Yejin Choi

NeurIPS Conference 2025 Conference Paper

AI Debate Aids Assessment of Controversial Claims

• Salman Rahman
• Sheriff Issaka
• Ashima Suvarna
• Genglin Liu
• James Shiffer
• Jaeyoung Lee
• Md Rizwan Parvez
• Hamid Palangi

As AI grows more powerful, it will increasingly shape how we understand the world. But with this influence comes the risk of amplifying misinformation and deepening social divides—especially on consequential topics where factual accuracy directly impacts well-being. Scalable Oversight aims to ensure AI systems remain truthful even when their capabilities exceed those of their evaluators. Yet when humans serve as evaluators, their own beliefs and biases can impair judgment. We study whether AI debate can guide biased judges toward the truth by having two AI systems debate opposing sides of controversial factuality claims on COVID-19 and climate change where people hold strong prior beliefs. We conduct two studies. Study I recruits human judges with either mainstream or skeptical beliefs who evaluate claims through two protocols: debate (interaction with two AI advisors arguing opposing sides) or consultancy (interaction with a single AI advisor). Study II uses AI judges with and without human-like personas to evaluate the same protocols. In Study I, debate consistently improves human judgment accuracy and confidence calibration, outperforming consultancy by 4-10\% across COVID-19 and climate change claims. The improvement is most significant for judges with mainstream beliefs (up to +15. 2\% accuracy on COVID-19 claims), though debate also helps skeptical judges who initially misjudge claims move toward accurate views (+4. 7\% accuracy). In Study II, AI judges with human-like personas achieve even higher accuracy (78. 5\%) than human judges (70. 1\%) and default AI judges without personas (69. 8\%), suggesting their potential for supervising frontier AI models. These findings highlight AI debate as a promising path toward scalable, bias-resilient oversight in contested domains.

NeurIPS Conference 2025 Conference Paper

Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)

• Liwei Jiang
• Yuanjun Chai
• Margaret Li
• Mickel Liu
• Raymond Fok
• Nouha Dziri
• Yulia Tsvetkov
• Maarten Sap

Large language models (LMs) often struggle to generate diverse, human-like creative content, raising concerns about the long-term homogenization of human thought through repeated exposure to similar outputs. Yet scalable methods for evaluating LM output diversity remain limited, especially beyond narrow tasks such as random number or name generation, or beyond repeated sampling from a single model. To address this gap, we introduce Infinity-Chat, a large-scale dataset of 26K diverse, real-world, open-ended user queries that admit a wide range of plausible answers with no single ground truth. We introduce the first comprehensive taxonomy for characterizing the full spectrum of open-ended prompts posed to LMs, comprising 6 top-level categories (e. g. , creative content generation, brainstorm & ideation) that further breaks down to 17 subcategories. Using Infinity-Chat, we present a large-scale study of mode collapse in LMs, revealing a pronounced Artificial Hivemind effect in open-ended generation of LMs, characterized by (1) intra-model repetition, where a single model consistently generates similar responses, and more so (2) inter-model homogeneity, where different models produce strikingly similar outputs. Infinity-Chat also includes 31, 250 human annotations, across absolute ratings and pairwise preferences, with 25 independent human annotations per example. This enables studying collective and individual-specific human preferences in response to open-ended queries. Our findings show that state-of-the-art LMs, reward models, and LM judges are less well calibrated to human ratings on model generations that elicit differing idiosyncratic annotator preferences, despite maintaining comparable overall quality. Overall, INFINITY-CHAT presents the first large-scale resource for systematically studying real-world open-ended queries to LMs, revealing critical insights to guide future research for mitigating long-term AI safety risks posed by the Artificial Hivemind.

NeurIPS Conference 2025 Conference Paper

Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations

• Brian Zheng
• Alisa Liu
• Orevaoghene Ahia
• Jonathan Hayase
• Yejin Choi
• Noah Smith

Modern tokenizers employ deterministic algorithms to map text into a single ``canonical" token sequence, yet the same string can be encoded as many non-canonical tokenizations using the language model vocabulary, including tokenizing by character. In this paper, we investigate the robustness of LMs to input encoded with non-canonical tokenizations entirely unseen during training. Surprisingly, when evaluated across 20 benchmarks, we find that instruction-tuned models retain up to 93. 4\% of their original performance when given a randomly sampled tokenization, and 90. 8\% with character-level tokenization. We find that overall stronger models tend to be more robust, and that robustness diminishes as the tokenization departs farther from the canonical form. Motivated by these results, we identify settings where non-canonical tokenization schemes can \textit{improve} performance, finding that character‑level segmentation improves string manipulation and code understanding tasks by up to 15\%, and right‑aligned digit grouping enhances large‑number arithmetic by over 33\%. Finally, we investigate the source of this robustness, finding that it arises in the instruction-tuning phase. We provide evidence that both base and post-trained models grasp the semantics of non-canonical tokenizations (perceiving them as containing misspellings). However, base models try to mimic the imagined mistakes and degenerate into nonsensical output, while post-trained models are committed to fluent responses. Overall, our findings suggest that models are less committed to their tokenizer than previously believed, and highlight the promise of intervening on tokenization at inference time to boost language model performance.

NeurIPS Conference 2025 Conference Paper

Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research

• A. Feder Cooper
• Christopher A. Choquette-Choo
• Miranda Bogen
• Kevin Klyman
• Matthew Jagielski
• Katja Filippova
• Ken Liu
• Alex Chouldechova

"Machine unlearning" is a popular proposed solution for mitigating the existence of content in an AI model that is problematic for legal or moral reasons, including privacy, copyright, safety, and more. For example, unlearning is often invoked as a solution for removing the effects of specific information from a generative-AI model's parameters, e. g. , a particular individual's personal data or the inclusion of copyrighted content in the model's training data. Unlearning is also proposed as a way to prevent a model from generating targeted types of information in its outputs, e. g. , generations that closely resemble a particular individual's data or reflect the concept of "Spiderman. " Both of these goals--the targeted removal of information from a model and the targeted suppression of information from a model's outputs--present various technical and substantive challenges. We provide a framework for ML researchers and policymakers to think rigorously about these challenges, identifying several mismatches between the goals of unlearning and feasible implementations. These mismatches explain why unlearning is not a general-purpose solution for circumscribing generative-AI model behavior in service of broader positive impact.

TMLR Journal 2025 Journal Article

Multi-Attribute Constraint Satisfaction via Language Model Rewriting

• Ashutosh Baheti
• Debanjana Chakraborty
• Faeze Brahman
• Ronan Le Bras
• Ximing Lu
• Nouha Dziri
• Yejin Choi
• Mark Riedl

Obeying precise constraints on top of multiple external attributes is a common computational problem underlying seemingly different domains, from controlled text generation to protein engineering. Existing language model (LM) controllability methods for multi-attribute constraint satisfaction often rely on specialized architectures or gradient-based classifiers, limiting their flexibility to work with arbitrary black-box evaluators and pretrained models. Current general-purpose large language models, while capable, cannot achieve fine-grained multi-attribute control over external attributes. Thus, we create Multi-Attribute Constraint Satisfaction (MACS), a generalized method capable of finetuning language models on any sequential domain to satisfy user-specified constraints on multiple external real-value attributes. Our method trains LMs as editors by sampling diverse multi-attribute edit pairs from an initial set of paraphrased outputs. During inference, LM iteratively improves upon its previous solution to satisfy constraints for all attributes by leveraging our designed constraint satisfaction reward. We additionally experiment with reward-weighted behavior cloning to further improve the constraint satisfaction rate of LMs. To evaluate our approach, we present a new Fine-grained Constraint Satisfaction (FineCS) benchmark, featuring two challenging tasks: (1) Text Style Transfer, where the goal is to simultaneously modify the sentiment and complexity of reviews, and (2) Protein Design, focusing on modulating fluorescence and stability of Green Fluorescent Proteins (GFP). Our empirical results show that MACS achieves the highest threshold satisfaction in both FineCS tasks, outperforming strong domain-specific baselines. Our work opens new avenues for generalized and real-value multi-attribute control, with implications for diverse applications spanning natural language processing and bioinformatics.

NeurIPS Conference 2025 Conference Paper

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

• Jaehun Jung
• Seungju Han
• Ximing Lu
• Skyler Hallinan
• David Acuna
• Shrimai Prabhumoye
• Mostofa Patwary
• Mohammad Shoeybi

Data diversity is crucial for training a strong language model. Yet metrics of diversity often diverge from this goal, measuring variations in heuristic features—like n-grams or embeddings—that are detached from how the model actually performs on a target task. This motivates us to ask: *Can we redefine data diversity—beyond measuring variations in heuristic features—in a way that better predicts model generalization? * Through large-scale empirical analyses spanning over 300 training runs, carefully controlled for data scale and quality, we show that data diversity can be a strong predictor of generalization in LLM reasoning—as measured by average model performance on unseen out-of-distribution benchmarks. We introduce **G-Vendi**, a metric that quantifies diversity via the entropy of model-induced loss gradients. G-Vendi scales to million-sample datasets and yet consistently outperforms heuristic alternatives, achieving strong correlation ($\text{Spearman's } \rho \approx 0. 9$) with out-of-distribution (OOD) performance across both natural language inference (NLI) and math reasoning tasks. Building on this insight, we present **Prismatic Synthesis**, a framework for generating diverse synthetic data by targeting underrepresented regions in gradient space. Experimental results show that Prismatic Synthesis consistently improves model performance as we scale synthetic data—not just on in-distribution test but across unseen, out-of-distribution benchmarks—significantly outperforming state-of-the-art models in both domains. For example, PrismMath-7B, our model distilled from a 32B LLM without human verification, outperforms R1-Distill-Qwen-7B—trained on proprietary data generated by 671B R1—on 6 out of 7 challenging math benchmarks.

NeurIPS Conference 2025 Conference Paper

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

• Mingjie Liu
• Shizhe Diao
• Ximing Lu
• Jian Hu
• Xin Dong
• Yejin Choi
• Jan Kautz
• Yi Dong

Recent advances in reasoning-centric language models have highlighted reinforcement learning (RL) as a promising method for aligning models with verifiable rewards. However, it remains contentious whether RL truly expands a model’s reasoning capabilities or merely amplifies high-reward outputs already latent in the base model’s distribution, and whether continually scaling up RL compute reliably leads to improved reasoning performance. In this work, we challenge prevailing assumptions by demonstrating that prolonged RL (ProRL) training can uncover novel reasoning strategies that are inaccessible to base models, even under extensive sampling. We introduce ProRL, a novel training methodology that incorporates KL divergence control, reference policy resetting, and a diverse suite of tasks. Our empirical analysis reveals that RL-trained models consistently outperform base models across a wide range of pass@$k$ evaluations, including scenarios where base models fail entirely regardless of the number of attempts. We further show that reasoning boundary improvements correlates strongly with task competence of base model and training duration, suggesting that RL can explore and populate new regions of solution space over time. These findings offer new insights into the conditions under which RL meaningfully expands reasoning boundaries in language models and establish a foundation for future work on long-horizon RL for reasoning. We will release model weights and data to support further research.

TMLR Journal 2025 Journal Article

RESTOR: Knowledge Recovery in Machine Unlearning

• Keivan Rezaei
• Khyathi Chandu
• Soheil Feizi
• Yejin Choi
• Faeze Brahman
• Abhilasha Ravichander

Large language models trained on web-scale corpora can memorize undesirable data containing misinformation, copyrighted material, or private or sensitive information. Recently, several machine unlearning algorithms have been proposed to eliminate the effect of such datapoints from trained models-- that is, to approximate *a model that had never been trained on these datapoints in the first place*. However, evaluating the effectiveness of unlearning algorithms remains an open challenge. Previous work has relied on heuristics-- such as verifying that the model can no longer reproduce the specific information targeted for removal while maintaining accuracy on unrelated test data. These approaches inadequately capture the complete effect of reversing the influence of datapoints on a trained model. In this work, we propose the RESTOR framework for machine unlearning evaluation, which assesses the ability of unlearning algorithms for targeted data erasure, by evaluating the ability of models to forget the knowledge introduced in these datapoints, while simultaneously recovering the model's knowledge state had it never encountered these datapoints. RESTOR helps uncover several novel insights about popular unlearning algorithms, and the mechanisms through which they operate-- for instance, identifying that some algorithms merely emphasize forgetting but not recovering knowledge, and that localizing unlearning targets can enhance unlearning performance.

NeurIPS Conference 2025 Conference Paper

VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents

• Kangrui Wang
• Pingyue Zhang
• Zihan Wang
• Yaning Gao
• Linjie Li
• Qineng Wang
• Hanyang Chen
• Yiping Lu

A major challenge in training VLM agents, compared to LLM agents, is that states shift from simple texts to complex visual observations, which introduces partial observability and demands robust world modeling. We ask: can VLM agents build internal world models through explicit visual state reasoning? In this work, we architecturally enforce and reward VLM agent’s reasoning process via reinforcement learning (RL), formulating the problem as a Partially Observable Markov Decision Process (POMDP). We demonstrate that structuring agent’s reasoning into StateEstimation (“what is the current state? ”) and TransitionModeling (“what is next? ”) is critical by studying five reasoning strategies. Investigating how agents should ground visual states and represent these internal beliefs, we reveal the optimal representations are task-dependent: Natural Language excels at capturing semantic relationships for general tasks, while Structured formats are essential for high-precision manipulation. These insights motivate our approach to reward shaping and credit assignment. We leverage a WorldModeling Reward to densely rewards the agent’s turn-by-turn state predictions, while our Bi-Level General Advantage Estimation (Bi-Level GAE) enables turn-aware credit assignment. Through such world model reasoning, we enable a 3B model to achieve performance of 0. 82 on a set of five diverse agent tasks, nearly 3× improvement over its untrained counterpart (0. 21) and surpassing proprietary reasoning models like GPT-5 (0. 75), Gemini 2. 5 Pro (0. 67) and Claude 4. 5 (0. 62). All experiments are supported by our VAGEN framework, a scalable system for training and analyzing multi-turn VLM agents across diverse visual environments

NeurIPS Conference 2025 Conference Paper

Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations

• Yiyou Sun
• Yu Gai
• Lijie Chen
• Abhilasha Ravichander
• Yejin Choi
• Nouha Dziri
• Dawn Song

Large language models (LLMs) frequently generate hallucinations—content that deviates from factually inaccurate or deviates from provided context—posing challenges for diagnosis. However, diagnosing the causes of hallucination is challenging due to the complex interplay of underlying causes. This paper introduces a framework to systematically understand the sources of hallucination behavior in large language models. Our key insight is that hallucinations arise when more frequent but non-factual associations outweigh faithful ones. Through theoretical and empirical analyses, we demonstrate that decoder-only transformers effectively function as subsequence embedding models, with the fully-connected layers encoding input-output associations. We propose a tracing algorithm that identifies causal subsequences by analyzing hallucination probabilities across randomized input contexts. Experiments show our method outperforms standard attribution techniques in identifying hallucination causes and is supported by evidence from the model’s training corpus. This work provides a unified perspective on hallucinations and a robust framework for their cause and analysis.

NeurIPS Conference 2024 Conference Paper

ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition

• Mohammadreza Salehi
• Jae S. Park
• Tanush Yadav
• Aditya Kusupati
• Ranjay Krishna
• Yejin Choi
• Hannaneh Hajishirzi
• Ali Farhadi

Our world is full of varied actions and moves in specialized fields that we, as humans, seek to identify and learn about. To evaluate the effectiveness of multi-modal models in helping us recognize such fine-grained actions, we introduce ActionAtlas, a video question answering (VideoQA) benchmark on fine-grained action recognition with short videos across various sports. ActionAtlas contains 554 videos spanning 284 actions across 42 sports with 1161 actions as total potential choices. Unlike most existing action recognition benchmarks that focus on simplistic actions, often identifiable from a single frame, ActionAtlas focuses on intricate movements and tests the models' ability to discern subtle differences. Additionally, each video in ActionAtlas also includes a question, which helps to more accurately pinpoint the action's performer in scenarios where multiple individuals are involved in different activities. We evaluate proprietary and open models on this benchmark and show that the state-of-the-art models only perform at most 48. 73% accurately where random chance is 20%. Furthermore, our results show that a high frame sampling rate is essential for recognizing actions in ActionAtlas, a feature that current top proprietary models like Gemini lack in their default settings.

NeurIPS Conference 2024 Conference Paper

Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions

• Jonathan Hayase
• Alisa Liu
• Yejin Choi
• Sewoong Oh
• Noah A. Smith

The pretraining data of today's strongest language models remains opaque, even when their parameters are open-sourced. In particular, little is known about the proportions of different domains, languages, or code represented in the data. While a long line of membership inference attacks aim to identify training examples on an instance level, they do not extend easily to global statistics about the corpus. In this work, we tackle a task which we call data mixture inference, which aims to uncover the distributional make-up of the pretraining data. We introduce a novel attack based on a previously overlooked source of information — byte-pair encoding (BPE) tokenizers, used by the vast majority of modern language models. Our key insight is that the ordered vocabulary learned by a BPE tokenizer naturally reveals information about the token frequencies in its training data: the first token is the most common byte pair, the second is the most common pair after merging the first token, and so on. Given a tokenizer's merge list along with data samples for each category of interest (e. g. , different natural languages), we formulate a linear program that solves for the relative proportion of each category in the tokenizer's training set. Importantly, to the extent to which tokenizer training data is representative of the pretraining data, we indirectly learn about the pretraining data. In controlled experiments, we show that our attack can recover mixture ratios with high precision for tokenizers trained on known mixtures of natural languages, programming languages, and data sources. We then apply our approach to off-the-shelf tokenizers released alongside recent LMs. We confirm much publicly disclosed information about these models, and also make several new inferences: GPT-4o is much more multilingual than its predecessors, training on 10x more non-English data than GPT-3. 5, Llama 3 and Claude are trained on predominantly code, and many recent models are trained on 7-16% books. We hope our work sheds light on current design practices for pretraining data, and inspires continued research into data mixture inference for LMs.

TMLR Journal 2024 Journal Article

Foundational Challenges in Assuring Alignment and Safety of Large Language Models

• Usman Anwar
• Abulhair Saparov
• Javier Rando
• Daniel Paleka
• Miles Turpin
• Peter Hase
• Ekdeep Singh Lubana
• Erik Jenner

This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs). These challenges are organized into three different categories: scientific understanding of LLMs, development and deployment methods, and sociotechnical challenges. Based on the identified challenges, we pose 200+, concrete research questions.

NeurIPS Conference 2024 Conference Paper

MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens

• Anas Awadalla
• Le Xue
• Oscar Lo
• Manli Shu
• Hannah Lee
• Etash Guha
• Matt Jordan
• Sheng Shen

Multimodal interleaved datasets featuring free-form interleaved sequences of images and text are crucial for training frontier large multimodal models (LMMs). Despite the rapid progression of open-source LMMs, there remains a pronounced scarcity of large-scale, open-source multimodal interleaved datasets. In response, we introduce MINT-1T, the most extensive and diverse open-source Multimodal INTerleaved dataset to date. MINT-1T comprises of one trillion text tokens and 3. 4 billion images, a 10x scale-up from existing open-source datasets. Additionally, we include previously untapped sources such as PDFs and ArXiv papers. As scaling multimodal interleaved datasets requires substantial engineering effort, sharing the data curation process and releasing the dataset greatly benefits the community. Our experiments show that LMMs trained on MINT-1T rival the performance of models trained on the previous leading dataset, OBELICS. We release our data at https: //github. com/mlfoundations/MINT-1T.

NeurIPS Conference 2024 Conference Paper

The Art of Saying No: Contextual Noncompliance in Language Models

• Faeze Brahman
• Sachin Kumar
• Vidhisha Balachandran
• Pradeep Dasigi
• Valentina Pyatkin
• Abhilasha Ravichander
• Sarah Wiegreffe
• Nouha Dziri

Chat-based language models are designed to be helpful, yet they should not comply with every user request. While most existing work primarily focuses on refusal of ``unsafe'' queries, we posit that the scope of noncompliance should be broadened. We introduce a comprehensive taxonomy of contextual noncompliance describing when and how models should not comply with user requests. Our taxonomy spans a wide range of categories including incomplete, unsupported, indeterminate, and humanizing requests (in addition to unsafe requests). To test noncompliance capabilities of language models, we use this taxonomy to develop a new evaluation suite of 1000 noncompliance prompts. We find that most existing models show significantly high compliance rates in certain previously understudied categories with models like GPT-4 incorrectly complying with as many as 30\% of requests. To address these gaps, we explore different training strategies using a synthetically-generated training set of requests and expected noncompliant responses. Our experiments demonstrate that while direct finetuning of instruction-tuned models can lead to both over-refusal and a decline in general capabilities, using parameter efficient methods like low rank adapters helps to strike a good balance between appropriate noncompliance and other capabilities.

NeurIPS Conference 2024 Conference Paper

Towards Visual Text Design Transfer Across Languages

• Yejin Choi
• Jiwan Chung
• Sumin Shim
• Giyeong Oh
• Youngjae Yu

Visual text design plays a critical role in conveying themes, emotions, and atmospheres in multimodal formats such as film posters and album covers. Translating these visual and textual elements across languages extends the concept of translation beyond mere text, requiring the adaptation of aesthetic and stylistic features. To address this, we introduce a novel task of Multimodal Style Translation (MuST-Bench), a benchmark designed to evaluate the ability of visual text generation models to perform translation across different writing systems while preserving design intent. Our initial experiments on MuST-Bench reveal that existing visual text generation models struggle with the proposed task due to the inadequacy of textual descriptions in conveying visual design. In response, we introduce SIGIL, a framework for multimodal style translation that eliminates the need for style descriptions. SIGIL enhances image generation models through three innovations: glyph latent for multilingual settings, pre-trained VAEs for stable style guidance, and an OCR model with reinforcement learning feedback for optimizing readable character generation. SIGIL outperforms existing baselines by achieving superior style consistency and legibility while maintaining visual fidelity, setting itself apart from traditional description-based approaches. We release MuST-Bench publicly for broader use and exploration https: //huggingface. co/datasets/yejinc/MuST-Bench.

NeurIPS Conference 2024 Conference Paper

Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback

• Hamish Ivison
• Yizhong Wang
• Jiacheng Liu
• Zeqiu Wu
• Valentina Pyatkin
• Nathan Lambert
• Noah A. Smith
• Yejin Choi

Learning from preference feedback has emerged as an essential step for improving the generation quality and performance of modern language models (LMs). Despite its widespread use, the way preference-based learning is applied varies wildly, with differing data, learning algorithms, and evaluations used, making disentangling the impact of each aspect difficult. In this work, we identify four core aspects of preference-based learning: preference data, learning algorithm, reward model, and policy training prompts, systematically investigate the impact of these components on downstream model performance, and suggest a recipe for strong learning for preference feedback. Our findings indicate that all aspects are important for performance, with better preference data leading to the largest improvements, followed by the choice of learning algorithm, the use of improved reward models, and finally the use of additional unlabeled prompts for policy training. Notably, PPO outperforms DPO by up to 2. 5% in math and 1. 2% in general domains. High-quality preference data leads to improvements of up to 8% in instruction following and truthfulness. Despite significant gains of up to 5% in mathematical evaluation when scaling up reward models, we surprisingly observe marginal improvements in other categories.

AAAI Conference 2024 Conference Paper

Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties

• Taylor Sorensen
• Liwei Jiang
• Jena D. Hwang
• Sydney Levine
• Valentina Pyatkin
• Peter West
• Nouha Dziri
• Ximing Lu

Human values are crucial to human decision-making. Value pluralism is the view that multiple correct values may be held in tension with one another (e.g., when considering lying to a friend to protect their feelings, how does one balance honesty with friendship?). As statistical learners, AI systems fit to averages by default, washing out these potentially irreducible value conflicts. To improve AI systems to better reflect value pluralism, the first-order challenge is to explore the extent to which AI systems can model pluralistic human values, rights, and duties as well as their interaction. We introduce ValuePrism, a large-scale dataset of 218k values, rights, and duties connected to 31k human-written situations. ValuePrism’s contextualized values are generated by GPT-4 and deemed high-quality by human annotators 91% of the time. We conduct a large-scale study with annotators across diverse social and demographic backgrounds to try to understand whose values are represented. With ValuePrism, we build Value Kaleidoscope (or Kaleido), an open, light-weight, and structured language-based multi-task model that generates, explains, and assesses the relevance and valence (i.e., support or oppose) of human values, rights, and duties within a specific context. Humans prefer the sets of values output by our system over the teacher GPT- 4, finding them more accurate and with broader coverage. In addition, we demonstrate that Kaleido can help explain variability in human decision-making by outputting contrasting values. Finally, we show that Kaleido’s representations transfer to other philosophical frameworks and datasets, confirming the benefit of an explicit, modular, and interpretable approach to value pluralism. We hope that our work will serve as a step to making more explicit the implicit values behind human decision-making and to steering AI systems to make decisions that are more in accordance with them.

NeurIPS Conference 2024 Conference Paper

WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

• Seungju Han
• Kavel Rao
• Allyson Ettinger
• Liwei Jiang
• Bill Yuchen Lin
• Nathan Lambert
• Yejin Choi
• Nouha Dziri

We introduce WildGuard---an open, light-weight moderation tool for LLM safety that achieves three goals: (1) identifying malicious intent in user prompts, (2) detecting safety risks of model responses, and (3) determining model refusal rate. Together, WildGuard serves the increasing needs for automatic safety moderation and evaluation of LLM interactions, providing a one-stop tool with enhanced accuracy and broad coverage across 13 risk categories. While existing open moderation tools such as Llama-Guard2 score reasonably well in classifying straightforward model interactions, they lag far behind a prompted GPT-4, especially in identifying adversarial jailbreaks and in evaluating models' refusals, a key measure for evaluating safety behaviors in model responses. To address these challenges, we construct WildGuardMix, a large-scale and carefully balanced multi-task safety moderation dataset with 92K labeled examples that cover vanilla (direct) prompts and adversarial jailbreaks, paired with various refusal and compliance responses. WildGuardMix is a combination of WildGuardTrain, the training data of WildGuard, and WildGuardTest, a high-quality human-annotated moderation test set with 5K labeled items covering broad risk scenarios. Through extensive evaluations on WildGuardTest and ten existing public benchmarks, we show that WildGuard establishes state-of-the-art performance in open-source safety moderation across all the three tasks compared to ten strong existing open-source moderation models (e. g. , up to 25. 3% improvement on refusal detection). Importantly, WildGuard matches and sometimes exceeds GPT-4 performance (e. g. , up to 4. 8% improvement on prompt harmfulness identification). WildGuard serves as a highly effective safety moderator in an LLM interface, reducing the success rate of jailbreak attacks from 79. 8% to 2. 4%. We will make all our data, models and training/evaluation code publicly available under CC BY 4. 0 license.

NeurIPS Conference 2024 Conference Paper

WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models

• Liwei Jiang
• Kavel Rao
• Seungju Han
• Allyson Ettinger
• Faeze Brahman
• Sachin Kumar
• Niloofar Mireshghallah
• Ximing Lu

We introduce WildTeaming, an automatic red-teaming framework that mines in-the-wild user-chatbot interactions to discover 5. 7K unique clusters of novel jailbreak tactics, and then composes selections of multiple mined tactics for systematic exploration of novel and even more challenging jailbreaks. Compared to prior work that performed red-teaming via recruited human workers, gradient-based optimization, or iterative revision with large language models (LLMs), our work investigates jailbreaks from chatbot users in-the-wild who were not specifically instructed to break the system. WildTeaming reveals previously unidentified vulnerabilities of frontier LLMs, resulting in more diverse and successful adversarial attacks compared to state-of-the-art jailbreaking methods. While there exist many datasets for jailbreak evaluation, very few open-source datasets exist for jailbreak training, as safety training data has been closed among all frontier models even when their weights are open. Therefore, with WildTeaming we create WildJailbreak, a large-scale open-source synthetic safety dataset with 262K vanilla (direct request) and adversarial (complex jailbreak) prompt-response pairs. In order to mitigate exaggerated safety behaviors, WildJailbreak provides two contrastive types of queries: 1) harmful queries (both vanilla and adversarial) and 2) benign queries that resemble harmful queries in form but contain no harmful intent. As WildJailbreak considerably upgrades the quality and scale of existing safety resources, it uniquely enables us to examine the scaling effects of data and the interplay of data properties and model capabilities during safety training. Through extensive model training and evaluations, we identify the training properties that enable an ideal balance of safety behaviors: appropriate safeguarding without over-refusal, effective handling of both vanilla and adversarial queries, and minimal, if any, decrease in general capabilities. All the components of WildJailbreak contribute to achieving balanced safety behaviors of models

NeurIPS Conference 2024 Conference Paper

WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences

• Yujie Lu
• Dongfu Jiang
• Wenhu Chen
• William Yang Wang
• Yejin Choi
• Bill Yuchen Lin

Recent breakthroughs in vision-language models (VLMs) emphasize the necessity of benchmarking human preferences in real-world multimodal interactions. To address this gap, we launched WildVision-Arena (WV-Arena), an online platform that collects human preferences to evaluate VLMs. We curated WV-Bench by selecting 500 high-quality samples from 8, 000 user submissions in WV-Arena. WV-Bench uses GPT-4 as the judge to compare each VLM with Claude-3-Sonnet, achieving a Spearman correlation of 0. 94 with the WV-Arena Elo. This significantly outperforms other benchmarks like MMVet, MMMU, and MMStar. Our comprehensive analysis of 20K real-world interactions reveals important insights into the failure cases of top-performing VLMs. For example, we find that although GPT-4V surpasses many other models like Reka-Flash, Opus, and Yi-VL-Plus in simple visual recognition and reasoning tasks, it still faces challenges with subtle contextual cues, spatial reasoning, visual imagination, and expert domain knowledge. Additionally, current VLMs exhibit issues with hallucinations and safety when intentionally provoked. We are releasing our chat and feedback data to further advance research in the field of VLMs.

TMLR Journal 2023 Journal Article

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

• Aarohi Srivastava
• Abhinav Rastogi
• Abhishek Rao
• Abu Awal Md Shoeb
• Abubakar Abid
• Adam Fisch
• Adam R. Brown
• Adam Santoro

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabilities are as yet poorly characterized. In order to inform future research, prepare for disruptive new model capabilities, and ameliorate socially harmful effects, it is vital that we understand the present and near-future capabilities and limitations of language models. To address this challenge, we introduce the Beyond the Imitation Game benchmark (BIG- bench). BIG-bench currently consists of 204 tasks, contributed by 450 authors across 132 institutions. Task topics are diverse, drawing problems from linguistics, childhood develop- ment, math, common-sense reasoning, biology, physics, social bias, software development, and beyond. BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models. We evaluate the behavior of OpenAI's GPT models, Google- internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters. In addition, a team of human expert raters performed all tasks in order to provide a strong baseline. Findings include: model performance and calibration both improve with scale, but are poor in absolute terms (and when compared with rater performance); performance is remarkably similar across model classes, though with benefits from sparsity; tasks that improve gradually and predictably commonly involve a large knowledge or memorization component, whereas tasks that exhibit "breakthrough" behavior at a critical scale often involve multiple steps or components, or brittle metrics; social bias typically increases with scale in settings with ambiguous context, but this can be improved with prompting.

AAMAS Conference 2023 Conference Paper

Common Sense: The Dark Matter of Language and Intelligence

• Yejin Choi

Scale appears to be the winning recipe in today’s leaderboards. And yet, extreme-scale neural models are (un)surprisingly brittle and make errors that are often nonsensical and even counterintuitive. In this talk, I will argue for the importance of knowledge, especially commonsense knowledge, as well as inference-time reasoning algorithms, and demonstrate how smaller models developed in academia can still have an edge over larger industry-scale models, if powered with knowledge and/or reasoning algorithms.

NeurIPS Conference 2023 Conference Paper

Faith and Fate: Limits of Transformers on Compositionality

• Nouha Dziri
• Ximing Lu
• Melanie Sclar
• Xiang (Lorraine) Li
• Liwei Jiang
• Bill Yuchen Lin
• Sean Welleck
• Peter West

Transformer large language models (LLMs) have sparked admiration for their exceptional performance on tasks that demand intricate multi-step reasoning. Yet, these models simultaneously show failures on surprisingly trivial problems. This begs the question: Are these errors incidental, or do they signal more substantial limitations? In an attempt to demystify transformer LLMs, we investigate the limits of these models across three representative compositional tasks---multi-digit multiplication, logic grid puzzles, and a classic dynamic programming problem. These tasks require breaking problems down into sub-steps and synthesizing these steps into a precise answer. We formulate compositional tasks as computation graphs to systematically quantify the level of complexity, and break down reasoning steps into intermediate sub-procedures. Our empirical findings suggest that transformer LLMs solve compositional tasks by reducing multi-step compositional reasoning into linearized subgraph matching, without necessarily developing systematic problem-solving skills. To round off our empirical study, we provide theoretical arguments on abstract multi-step reasoning problems that highlight how autoregressive generations' performance can rapidly decay with increased task complexity.

NeurIPS Conference 2023 Conference Paper

Localized Symbolic Knowledge Distillation for Visual Commonsense Models

• Jae Sung Park
• Jack Hessel
• Khyathi Chandu
• Paul Pu Liang
• Ximing Lu
• Peter West
• Youngjae Yu
• Qiuyuan Huang

Instruction following vision-language (VL) models offer a flexibleinterface that supports a broad range of multimodal tasks in a zero-shot fashion. However, interfaces that operate on full images do not directly enable the user to“point to" and access specific regions within images. This capability is importantnot only to support reference-grounded VL benchmarks, but also, for practicalapplications that require precise within-image reasoning. We build LocalizedVisual Commonsense model which allows users to specify (multiple) regions-as-input. We train our model by sampling localized commonsense knowledgefrom a large language model (LLM): specifically, we prompt a LLM to collectcommonsense knowledge given a global literal image description and a localliteral region description automatically generated by a set of VL models. Thispipeline is scalable and fully automatic, as no aligned or human-authored imageand text pairs are required. With a separately trained critic model that selectshigh quality examples, we find that training on the localized commonsense corpusexpanded solely from images can successfully distill existing VL models to supporta reference-as-input interface. Empirical results and human evaluations in zero-shotsettings demonstrate that our distillation method results in more precise VL modelsof reasoning compared to a baseline of passing a generated referring expression.

JMLR Journal 2023 Journal Article

MAUVE Scores for Generative Models: Theory and Practice

• Krishna Pillutla
• Lang Liu
• John Thickstun
• Sean Welleck
• Swabha Swayamdipta
• Rowan Zellers
• Sewoong Oh
• Yejin Choi

Generative artificial intelligence has made significant strides, producing text indistinguishable from human prose and remarkably photorealistic images. Automatically measuring how close the generated data distribution is to the target distribution is central to diagnosing existing models and developing better ones. We present MAUVE, a family of comparison measures between pairs of distributions such as those encountered in the generative modeling of text or images. These scores are statistical summaries of divergence frontiers capturing two types of errors in generative modeling. We explore three approaches to statistically estimate these scores: vector quantization, non-parametric estimation, and classifier-based estimation. We provide statistical bounds for the vector quantization approach. Empirically, we find that the proposed scores paired with a range of $f$-divergences and statistical estimation methods can quantify the gaps between the distributions of human-written text and those of modern neural language models by correlating with human judgments and identifying known properties of the generated texts. We demonstrate in the vision domain that MAUVE can identify known properties of generated images on par with or better than existing metrics. In conclusion, we present practical recommendations for using MAUVE effectively with language and image modalities. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2023. ( edit, beta )

NeurIPS Conference 2023 Conference Paper

Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text

• Wanrong Zhu
• Jack Hessel
• Anas Awadalla
• Samir Yitzhak Gadre
• Jesse Dodge
• Alex Fang
• Youngjae Yu
• Ludwig Schmidt

In-context vision and language models like Flamingo support arbitrarily interleaved sequences of images and text as input. This format not only enables few-shot learning via interleaving independent supervised (image, text) examples, but also, more complex prompts involving interaction between images, e. g. , ``What do image A and image B have in common? ''To support this interface, pretraining occurs over web corpora that similarly contain interleaved images+text. To date, however, large-scale data of this form have not been publicly available. We release Multimodal C4, an augmentation of the popular text-only C4 corpus with images interleaved. We use a linear assignment algorithm to place images into longer bodies of text using CLIP features, a process that we show outperforms alternatives. Multimodal C4 spans everyday topics like cooking, travel, technology, etc. A manual inspection of a random sample of documents shows that a vast majority (88\%) of images are topically relevant, and that linear assignment frequently selects individual sentences specifically well-aligned with each image (80\%). After filtering NSFW images, ads, etc. , the resulting corpus consists of 101. 2M documents with 571M images interleaved in 43B English tokens.

NeurIPS Conference 2023 Conference Paper

RealTime QA: What's the Answer Right Now?

• Jungo Kasai
• Keisuke Sakaguchi
• yoichi takahashi
• Ronan Le Bras
• Akari Asai
• Xinyan Yu
• Dragomir Radev
• Noah A. Smith

We introduce RealTime QA, a dynamic question answering (QA) platform that announces questions and evaluates systems on a regular basis (weekly in this version). RealTime QA inquires about the current world, and QA systems need to answer questions about novel events or information. It therefore challenges static, conventional assumptions in open-domain QA datasets and pursues instantaneous applications. We build strong baseline models upon large pretrained language models, including GPT-3 and T5. Our benchmark is an ongoing effort, and this paper presents real-time evaluation results over the past year. Our experimental results show that GPT-3 can often properly update its generation results, based on newly-retrieved documents, highlighting the importance of up-to-date information retrieval. Nonetheless, we find that GPT-3 tends to return outdated answers when retrieved documents do not provide sufficient information to find an answer. This suggests an important avenue for future research: can an open-domain QA system identify such unanswerable cases and communicate with the user or even the retrieval module to modify the retrieval results? We hope that RealTime QA will spur progress in instantaneous applications of question answering and beyond.

NeurIPS Conference 2023 Conference Paper

SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks

• Bill Yuchen Lin
• Yicheng Fu
• Karina Yang
• Faeze Brahman
• Shiyu Huang
• Chandra Bhagavatula
• Prithviraj Ammanabrolu
• Yejin Choi

We introduce SwiftSage, a novel agent framework inspired by the dual-process theory of human cognition, designed to excel in action planning for complex interactive reasoning tasks. SwiftSage integrates the strengths of behavior cloning and prompting large language models (LLMs) to enhance task completion performance. The framework comprises two primary modules: the Swift module, representing fast and intuitive thinking, and the Sage module, emulating deliberate thought processes. The Swift module is a small encoder-decoder LM fine-tuned on the oracle agent's action trajectories, while the Sage module employs LLMs such as GPT-4 for subgoal planning and grounding. We develop a heuristic method to harmoniously integrate the two modules, resulting in a more efficient and robust problem-solving process. In 30 tasks from the ScienceWorld benchmark, SwiftSage significantly outperforms other methods such as SayCan, ReAct, and Reflexion, demonstrating its effectiveness in solving complex interactive tasks.

NeurIPS Conference 2022 Conference Paper

COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics

• Lianhui Qin
• Sean Welleck
• Daniel Khashabi
• Yejin Choi

Many applications of text generation require incorporating different constraints to control the semantics or style of generated text. These constraints can be hard (e. g. , ensuring certain keywords are included in the output) and soft (e. g. , contextualizing the output with the left- or right-hand context). In this paper, we present Energy-based Constrained Decoding with Langevin Dynamics (COLD), a decoding framework which unifies constrained generation as specifying constraints through an energy function, then performing efficient differentiable reasoning over the constraints through gradient-based sampling. COLD decoding is a flexible framework that can be applied directly to off-the-shelf left-to-right language models without the need for any task-specific fine-tuning, as demonstrated through three challenging text generation applications: lexically-constrained generation, abductive reasoning, and counterfactual reasoning. Our experiments on these constrained generation tasks point to the effectiveness of our approach, both in terms of automatic and human evaluation.

NeurIPS Conference 2022 Conference Paper

NaturalProver: Grounded Mathematical Proof Generation with Language Models

• Sean Welleck
• Jiacheng Liu
• Ximing Lu
• Hannaneh Hajishirzi
• Yejin Choi

Theorem proving in natural mathematical language – the mixture of symbolic and natural language used by humans – plays a central role in mathematical advances and education, and tests aspects of reasoning that are core to intelligence. Yet it has remained underexplored with modern generative models. We study large-scale language models on two new generation tasks: suggesting the next step in a mathematical proof, and full proof generation. We develop NaturalProver, a language model that generates proofs by conditioning on background references (e. g. theorems and definitions that are either retrieved or human-provided), and optionally enforces their presence with constrained decoding. On theorems from the NaturalProofs benchmark, NaturalProver improves the quality of next-step suggestions and generated proofs over fine-tuned GPT-3, according to human evaluations from university-level mathematics students. NaturalProver is capable of proving some theorems that require short (2-6 step) proofs, and providing next-step suggestions that are rated as correct and useful over 40% of the time, which is to our knowledge the first demonstration of these capabilities using neural language models.

NeurIPS Conference 2022 Conference Paper

QUARK: Controllable Text Generation with Reinforced Unlearning

• Ximing Lu
• Sean Welleck
• Jack Hessel
• Liwei Jiang
• Lianhui Qin
• Peter West
• Prithviraj Ammanabrolu
• Yejin Choi

Large-scale language models often learn behaviors that are misaligned with user expectations. Generated text may contain offensive or toxic language, contain significant repetition, or be of a different sentiment than desired by the user. We consider the task of unlearning these misalignments by fine-tuning the language model on signals of what not to do. We introduce Quantized Reward Konditioning (Quark), an algorithm for optimizing a reward function that quantifies an (un)wanted property, while not straying too far from the original model. Quark alternates between (i) collecting samples with the current language model, (ii) sorting them into quantiles based on reward, with each quantile identified by a reward token prepended to the language model’s input, and (iii) using a standard language modeling loss on samples from each quantile conditioned on its reward token, while remaining nearby the original language model via a KL-divergence penalty. By conditioning on a high-reward token at generation time, the model generates text that exhibits less of the unwanted property. For unlearning toxicity, negative sentiment, and repetition, our experiments show that Quark outperforms both strong baselines and state-of-the-art reinforcement learning methods like PPO, while relying only on standard language modeling primitives.

AAAI Conference 2022 Conference Paper

Symbolic Brittleness in Sequence Models: On Systematic Generalization in Symbolic Mathematics

• Sean Welleck
• Peter West
• Jize Cao
• Yejin Choi

Neural sequence models trained with maximum likelihood estimation have led to breakthroughs in many tasks, where success is defined by the gap between training and test performance. However, their ability to achieve stronger forms of generalization remains unclear. We consider the problem of symbolic mathematical integration, as it requires generalizing systematically beyond the test set. We develop a methodology for evaluating generalization that takes advantage of the problem domain’s structure and access to a verifier. Despite promising in-distribution performance of sequenceto-sequence models in this domain, we demonstrate challenges in achieving robustness, compositionality, and outof-distribution generalization, through both carefully constructed manual test suites and a genetic algorithm that automatically finds large collections of failures in a controllable manner. Our investigation highlights the difficulty of generalizing well with the predominant modeling and learning approach, and the importance of evaluating beyond the test set, across different aspects of generalization.

AAAI Conference 2021 Conference Paper

(Comet-) Atomic 2020: On Symbolic and Neural Commonsense Knowledge Graphs

• Jena D. Hwang
• Chandra Bhagavatula
• Ronan Le Bras
• Jeff Da
• Keisuke Sakaguchi
• Antoine Bosselut
• Yejin Choi

Recent years have brought about a renewed interest in commonsense representation and reasoning in the field of natural language understanding. The development of new commonsense knowledge graphs (CSKG) has been central to these advances as their diverse facts can be used and referenced by machine learning models for tackling new and challenging tasks. At the same time, there remain questions about the quality and coverage of these resources due to the massive scale required to comprehensively encompass general commonsense knowledge. In this work, we posit that manually constructed CSKGs will never achieve the coverage necessary to be applicable in all situations encountered by NLP agents. Therefore, we propose a new evaluation framework for testing the utility of KGs based on how effectively implicit knowledge representations can be learned from them. With this new goal, we propose ATOMIC 20 20, a new CSKG of general-purpose commonsense knowledge containing knowledge that is not readily available in pretrained language models. We evaluate its properties in comparison with other leading CSKGs, performing the first large-scale pairwise study of commonsense knowledge resources. Next, we show that ATOMIC 20 20 is better suited for training knowledge models that can generate accurate, representative knowledge for new, unseen entities and events. Finally, through human evaluation, we show that the few-shot performance of GPT-3 (175B parameters), while impressive, remains ∼12 absolute points lower than a BART-based knowledge model trained on ATOMIC 20 20 despite using over 430x fewer parameters.

NeurIPS Conference 2021 Conference Paper

CommonsenseQA 2.0: Exposing the Limits of AI through Gamification

• Alon Talmor
• Ori Yoran
• Ronan Le Bras
• Chandra Bhagavatula
• Yoav Goldberg
• Yejin Choi
• Jonathan Berant

Constructing benchmarks that test the abilities of modern natural language understanding models is difficult - pre-trained language models exploit artifacts in benchmarks to achieve human parity, but still fail on adversarial examples and make errors that demonstrate a lack of common sense. In this work, we propose gamification as a framework for data construction. The goal of players in the game is to compose questions that mislead a rival AI while using specific phrases for extra points. The game environment leads to enhanced user engagement and simultaneously gives the game designer control over the collected data, allowing us to collect high-quality data at scale. Using our method we create CommonsenseQA 2. 0, which includes 14, 343 yes/no questions, and demonstrate its difficulty for models that are orders-of-magnitude larger than the AI used in the game itself. Our best baseline, the T5-based Unicorn with 11B parameters achieves an accuracy of 70. 2%, substantially higher than GPT-3 (52. 9%) in a few-shot inference setup. Both score well below human performance which is at 94. 1%.

NeurIPS Conference 2021 Conference Paper

Divergence Frontiers for Generative Models: Sample Complexity, Quantization Effects, and Frontier Integrals

• Lang Liu
• Krishna Pillutla
• Sean Welleck
• Sewoong Oh
• Yejin Choi
• Zaid Harchaoui

The spectacular success of deep generative models calls for quantitative tools to measure their statistical performance. Divergence frontiers have recently been proposed as an evaluation framework for generative models, due to their ability to measure the quality-diversity trade-off inherent to deep generative modeling. We establish non-asymptotic bounds on the sample complexity of divergence frontiers. We also introduce frontier integrals which provide summary statistics of divergence frontiers. We show how smoothed estimators such as Good-Turing or Krichevsky-Trofimov can overcome the missing mass problem and lead to faster rates of convergence. We illustrate the theoretical results with numerical examples from natural language processing and computer vision.

AAAI Conference 2021 Conference Paper

Dynamic Neuro-Symbolic Knowledge Graph Construction for Zero-shot Commonsense Question Answering

• Antoine Bosselut
• Ronan Le Bras
• Yejin Choi

Understanding narratives requires reasoning about implicit world knowledge related to the causes, effects, and states of situations described in text. At the core of this challenge is how to access contextually relevant knowledge on demand and reason over it. In this paper, we present initial studies toward zero-shot commonsense question answering by formulating the task as inference over dynamically generated commonsense knowledge graphs. In contrast to previous studies for knowledge integration that rely on retrieval of existing knowledge from static knowledge graphs, our study requires commonsense knowledge integration where contextually relevant knowledge is often not present in existing knowledge bases. Therefore, we present a novel approach that generates contextually-relevant symbolic knowledge structures on demand using generative neural commonsense knowledge models. Empirical results on two datasets demonstrate the efficacy of our neuro-symbolic approach for dynamically constructing knowledge graphs for reasoning. Our approach achieves significant performance boosts over pretrained language models and vanilla knowledge models, all while providing interpretable reasoning paths for its predictions.

AAAI Conference 2021 Conference Paper

Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision

• Faeze Brahman
• Vered Shwartz
• Rachel Rudinger
• Yejin Choi

The black-box nature of neural models has motivated a line of research that aims to generate natural language rationales to explain why a model made certain predictions. Such rationale generation models, to date, have been trained on datasetspecific crowdsourced rationales, but this approach is costly and is not generalizable to new tasks and domains. In this paper, we investigate the extent to which neural models can reason about natural language rationales that explain model predictions, relying only on distant supervision with no additional annotation cost for human-written rationales. We investigate multiple ways to automatically generate rationales using pre-trained language models, neural knowledge models, and distant supervision from related tasks, and train generative models capable of composing explanatory rationales for unseen instances. We demonstrate our approach on the defeasible inference task, a nonmonotonic reasoning task in which an inference may be strengthened or weakened when new information (an update) is introduced. Our model shows promises at generating post-hoc rationales explaining why an inference is more or less likely given the additional information, however, it mostly generates trivial rationales reflecting the fundamental limitations of neural language models. Conversely, the more realistic setup of jointly predicting the update or its type and generating rationale is more challenging, suggesting an important future direction.

NeurIPS Conference 2021 Conference Paper

MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers

• Krishna Pillutla
• Swabha Swayamdipta
• Rowan Zellers
• John Thickstun
• Sean Welleck
• Yejin Choi
• Zaid Harchaoui

As major progress is made in open-ended text generation, measuring how close machine-generated text is to human language remains a critical open problem. We introduce Mauve, a comparison measure for open-ended text generation, which directly compares the learnt distribution from a text generation model to the distribution of human-written text using divergence frontiers. Mauve scales up to modern text generation models by computing information divergences in a quantized embedding space. Through an extensive empirical study on three open-ended generation tasks, we find that Mauve identifies known properties of generated text, scales naturally with model size, and correlates with human judgments, with fewer restrictions than existing distributional evaluation metrics.

NeurIPS Conference 2021 Conference Paper

MERLOT: Multimodal Neural Script Knowledge Models

• Rowan Zellers
• Ximing Lu
• Jack Hessel
• Youngjae Yu
• Jae Sung Park
• Jize Cao
• Ali Farhadi
• Yejin Choi

As humans, we understand events in the visual world contextually, performing multimodal reasoning across time to make inferences about the past, present, and future. We introduce MERLOT, a model that learns multimodal script knowledge by watching millions of YouTube videos with transcribed speech -- in an entirely label-free, self-supervised manner. By pretraining with a mix of both frame-level (spatial) and video-level (temporal) objectives, our model not only learns to match images to temporally corresponding words, but also to contextualize what is happening globally over time. As a result, MERLOT exhibits strong out-of-the-box representations of temporal commonsense, and achieves state-of-the-art performance on 12 different video QA datasets when finetuned. It also transfers well to the world of static images, allowing models to reason about the dynamic context behind visual scenes. On Visual Commonsense Reasoning, MERLOT~answers questions correctly with 80. 6\% accuracy, outperforming state-of-the-art models of similar size by over 3\%, even those that make heavy use of auxiliary supervised data (like object bounding boxes). Ablation analyses demonstrate the complementary importance of: 1) training on videos versus static images; 2) scaling the magnitude and diversity of the pretraining video corpus; and 3) using diverse objectives that encourage full-stack multimodal reasoning, from the recognition to cognition level.

AAAI Conference 2021 Conference Paper

MultiTalk: A Highly-Branching Dialog Testbed for Diverse Conversations

• Yao Dou
• Maxwell Forbes
• Ari Holtzman
• Yejin Choi

We study conversational dialog in which there are many possible responses to a given history. We present the MultiTalk Dataset, a corpus of over 320, 000 sentences of written conversational dialog that balances a high branching factor (10) with several conversation turns (6) through selective branch continuation. We make multiple contributions to study dialog generation in the highly branching setting. In order to evaluate a diverse set of generations, we propose a simple scoring algorithm, based on bipartite graph matching, to optimally incorporate a set of diverse references. We study multiple language generation tasks at different levels of predictive conversation depth, using textual attributes induced automatically from pretrained classifiers. Our culminating task is a challenging theory of mind problem, a controllable generation task which requires reasoning about the expected reaction of the listener.

NeurIPS Conference 2021 Conference Paper

NaturalProofs: Mathematical Theorem Proving in Natural Language

• Sean Welleck
• Jiacheng Liu
• Ronan Le Bras
• Hanna Hajishirzi
• Yejin Choi
• Kyunghyun Cho

Understanding and creating mathematics using natural mathematical language - the mixture of symbolic and natural language used by humans - is a challenging and important problem for driving progress in machine learning. As a step in this direction, we develop NaturalProofs, a multi-domain corpus of mathematical statements and their proofs, written in natural mathematical language. NaturalProofs unifies broad coverage, deep coverage, and low-resource mathematical sources, allowing for evaluating both in-distribution and zero-shot generalization. Using NaturalProofs, we benchmark strong neural methods on mathematical reference retrieval and generation tasks which test a system's ability to determine key results that appear in a proof. Large-scale sequence models show promise compared to classical information retrieval methods, yet their performance and out-of-domain generalization leave substantial room for improvement. NaturalProofs opens many avenues for research on challenging mathematical tasks.

AAAI Conference 2021 Conference Paper

Paragraph-level Commonsense Transformers with Recurrent Memory

• Saadia Gabriel
• Chandra Bhagavatula
• Vered Shwartz
• Ronan Le Bras
• Maxwell Forbes
• Yejin Choi

Human understanding of narrative texts requires making commonsense inferences beyond what is stated explicitly in the text. A recent model, COMET, can generate such implicit commonsense inferences along several dimensions such as pre- and post-conditions, motivations, and mental states of the participants. However, COMET was trained on commonsense inferences of short phrases, and is therefore discourseagnostic. When presented with each sentence of a multisentence narrative, it might generate inferences that are inconsistent with the rest of the narrative. We present the task of discourse-aware commonsense inference. Given a sentence within a narrative, the goal is to generate commonsense inferences along predefined dimensions, while maintaining coherence with the rest of the narrative. Such large-scale paragraph-level annotation is hard to get and costly, so we use available sentence-level annotations to efficiently and automatically construct a distantly supervised corpus. Using this corpus, we train PARA-COMET, a discourseaware model that incorporates paragraph-level information to generate coherent commonsense inferences from narratives. PARA-COMET captures both semantic knowledge pertaining to prior world knowledge, and episodic knowledge involving how current events relate to prior and future events in a narrative. Our results show that PARA-COMET outperforms the sentence-level baselines, particularly in generating inferences that are both coherent and novel.

AAAI Conference 2021 Conference Paper

SCRUPLES: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotes

• Nicholas Lourie
• Ronan Le Bras
• Yejin Choi

As AI systems become an increasing part of people’s everyday lives, it becomes ever more important that they understand people’s ethical norms. Motivated by descriptive ethics, a field of study that focuses on people’s descriptive judgments rather than theoretical prescriptions on morality, we investigate a novel, data-driven approach to machine ethics. We introduce SCRUPLES, the first large-scale dataset with 625, 000 ethical judgments over 32, 000 real-life anecdotes. Each anecdote recounts a complex ethical situation, often posing moral dilemmas, paired with a distribution of judgments contributed by the community members. Our dataset presents a major challenge to state-of-the-art neural language models, leaving significant room for improvement. However, when presented with simplified moral situations, the results are considerably more promising, suggesting that neural models can effectively learn simpler ethical building blocks. A key take-away of our empirical analysis is that norms are not always clean-cut; many situations are naturally divisive. We present a new method to estimate the best possible performance on such tasks with inherently diverse label distributions, and explore likelihood functions that separate intrinsic from model uncertainty. Data and code are available at https: //github. com/allenai/scruples.

AAAI Conference 2021 Conference Paper

UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark

• Nicholas Lourie
• Ronan Le Bras
• Chandra Bhagavatula
• Yejin Choi

Commonsense AI has long been seen as a near impossible goal—until recently. Now, research interest has sharply increased with an influx of new benchmarks and models. We propose two new ways to evaluate commonsense models, emphasizing their generality on new tasks and building on diverse, recently introduced benchmarks. First, we propose a new multitask benchmark, RAINBOW, to promote research on commonsense models that generalize well over multiple tasks and datasets. Second, we propose a novel evaluation, the cost equivalent curve, that sheds new insight on how the choice of source datasets, pretrained language models, and transfer learning methods impacts performance and data efficiency. We perform extensive experiments—over 200 experiments encompassing 4800 models—and report multiple valuable and sometimes surprising findings, e. g. , that transfer almost always leads to better or equivalent performance if following a particular recipe, that QA-based commonsense datasets transfer well with each other, while commonsense knowledge graphs do not, and that perhaps counter-intuitively, larger models benefit more from transfer than smaller ones. Last but not least, we introduce a new universal commonsense reasoning model, UNICORN, that establishes new state-of-the-art performance across 8 popular commonsense benchmarks, αNLI (→87. 3%), COSMOSQA (→91. 8%), HELLASWAG (→93. 9%), PIQA (→90. 1%), SOCIALIQA (→83. 2%), WINOGRANDE (→86. 6%), CYCIC (→94. 0%) and COMMONSENSEQA (→79. 3%).

AAAI Conference 2020 Conference Paper

Commonsense Knowledge Base Completion with Structural and Semantic Context

• Chaitanya Malaviya
• Chandra Bhagavatula
• Antoine Bosselut
• Yejin Choi

Automatic KB completion for commonsense knowledge graphs (e. g. , ATOMIC and ConceptNet) poses unique challenges compared to the much studied conventional knowledge bases (e. g. , Freebase). Commonsense knowledge graphs use free-form text to represent nodes, resulting in orders of magnitude more nodes compared to conventional KBs ( ∼18x more nodes in ATOMIC compared to Freebase (FB15K- 237)). Importantly, this implies significantly sparser graph structures — a major challenge for existing KB completion methods that assume densely connected graphs over a relatively smaller set of nodes. In this paper, we present novel KB completion models that can address these challenges by exploiting the structural and semantic context of nodes. Specifically, we investigate two key ideas: (1) learning from local graph structure, using graph convolutional networks and automatic graph densification and (2) transfer learning from pre-trained language models to knowledge graphs for enhanced contextual representation of knowledge. We describe our method to incorporate information from both these sources in a joint model and provide the first empirical results for KB completion on ATOMIC and evaluation with ranking metrics on ConceptNet. Our results demonstrate the effectiveness of language model representations in boosting link prediction performance and the advantages of learning from local graph structure (+1. 5 points in MRR for ConceptNet) when training on subgraphs for computational efficiency. Further analysis on model predictions shines light on the types of commonsense knowledge that language models capture well. 1

AAAI Conference 2020 Conference Paper

PIQA: Reasoning about Physical Commonsense in Natural Language

• Yonatan Bisk
• Rowan Zellers
• Ronan Le Bras
• Jianfeng Gao
• Yejin Choi

To apply eyeshadow without a brush, should I use a cotton swab or a toothpick? Questions requiring this kind of physical commonsense pose a challenge to today’s natural language understanding systems. While recent pretrained models (such as BERT) have made progress on question answering over more abstract domains – such as news articles and encyclopedia entries, where text is plentiful – in more physical domains, text is inherently limited due to reporting bias. Can AI systems learn to reliably answer physical commonsense questions without experiencing the physical world? In this paper, we introduce the task of physical commonsense reasoning and a corresponding benchmark dataset Physical Interaction: Question Answering or PIQA. Though humans find the dataset easy (95% accuracy), large pretrained models struggle (∼75%). We provide analysis about the dimensions of knowledge that existing models lack, which offers significant opportunities for future research.

AAAI Conference 2020 Conference Paper

WinoGrande: An Adversarial Winograd Schema Challenge at Scale

• Keisuke Sakaguchi
• Ronan Le Bras
• Chandra Bhagavatula
• Yejin Choi

The Winograd Schema Challenge (WSC) (Levesque, Davis, and Morgenstern 2011), a benchmark for commonsense reasoning, is a set of 273 expert-crafted pronoun resolution problems originally designed to be unsolvable for statistical models that rely on selectional preferences or word associations. However, recent advances in neural language models have already reached around 90% accuracy on variants of WSC. This raises an important question whether these models have truly acquired robust commonsense capabilities or whether they rely on spurious biases in the datasets that lead to an overestimation of the true capabilities of machine commonsense. To investigate this question, we introduce WINOGRANDE, a large-scale dataset of 44k problems, inspired by the original WSC design, but adjusted to improve both the scale and the hardness of the dataset. The key steps of the dataset construction consist of (1) a carefully designed crowdsourcing procedure, followed by (2) systematic bias reduction using a novel AFLITE algorithm that generalizes human-detectable word associations to machine-detectable embedding associations. The best state-of-the-art methods on WINOGRANDE achieve 59. 4 – 79. 1%, which are ∼15-35% (absolute) below human performance of 94. 0%, depending on the amount of the training data allowed (2% – 100% respectively). Furthermore, we establish new state-of-the-art results on five related benchmarks — WSC (→ 90. 1%), DPR (→ 93. 1%), COPA(→ 90. 6%), KnowRef (→ 85. 6%), and Winogender (→ 97. 1%). These results have dual implications: on one hand, they demonstrate the effectiveness of WINOGRANDE when used as a resource for transfer learning. On the other hand, they raise a concern that we are likely to be overestimating the true capabilities of machine commonsense across all these benchmarks. We emphasize the importance of algorithmic bias reduction in existing and future benchmarks to mitigate such overestimation.

AAAI Conference 2019 Conference Paper

ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning

• Maarten Sap
• Ronan Le Bras
• Emily Allaway
• Chandra Bhagavatula
• Nicholas Lourie
• Hannah Rashkin
• Brendan Roof
• Noah A. Smith

We present ATOMIC, an atlas of everyday commonsense reasoning, organized through 877k textual descriptions of inferential knowledge. Compared to existing resources that center around taxonomic knowledge, ATOMIC focuses on inferential knowledge organized as typed if-then relations with variables (e. g. , “if X pays Y a compliment, then Y will likely return the compliment”). We propose nine if-then relation types to distinguish causes vs. effects, agents vs. themes, voluntary vs. involuntary events, and actions vs. mental states. By generatively training on the rich inferential knowledge described in ATOMIC, we show that neural models can acquire simple commonsense capabilities and reason about previously unseen events. Experimental results demonstrate that multitask models that incorporate the hierarchical structure of if-then relation types lead to more accurate inference compared to models trained in isolation, as measured by both automatic and human evaluation.

NeurIPS Conference 2019 Conference Paper

Defending Against Neural Fake News

• Rowan Zellers
• Ari Holtzman
• Hannah Rashkin
• Yonatan Bisk
• Ali Farhadi
• Franziska Roesner
• Yejin Choi

Recent progress in natural language generation has raised dual-use concerns. While applications like summarization and translation are positive, the underlying technology also might enable adversaries to generate neural fake news: targeted propaganda that closely mimics the style of real news. Modern computer security relies on careful threat modeling: identifying potential threats and vulnerabilities from an adversary's point of view, and exploring potential mitigations to these threats. Likewise, developing robust defenses against neural fake news requires us first to carefully investigate and characterize the risks of these models. We thus present a model for controllable text generation called Grover. Given a headline like 'Link Found Between Vaccines and Autism, ' Grover can generate the rest of the article; humans find these generations to be more trustworthy than human-written disinformation. Developing robust verification techniques against generators like Grover is critical. We find that best current discriminators can classify neural fake news from real, human-written, news with 73% accuracy, assuming access to a moderate level of training data. Counterintuitively, the best defense against Grover turns out to be Grover itself, with 92% accuracy, demonstrating the importance of public release of strong generators. We investigate these results further, showing that exposure bias -- and sampling strategies that alleviate its effects -- both leave artifacts that similar discriminators can pick up on. We conclude by discussing ethical issues regarding the technology, and plan to release Grover publicly, helping pave the way for better detection of neural fake news.

AAAI Conference 2018 Conference Paper

Learning Interpretable Spatial Operations in a Rich 3D Blocks World

• Yonatan Bisk
• Kevin Shih
• Yejin Choi
• Daniel Marcu

In this paper, we study the problem of mapping natural language instructions to complex spatial actions in a 3D blocks world. We first introduce a new dataset that pairs complex 3D spatial operations to rich natural language descriptions that require complex spatial and pragmatic interpretations such as “mirroring”, “twisting”, and “balancing”. This dataset, built on the simulation environment of Bisk, Yuret, and Marcu (2016), attains language that is significantly richer and more complex, while also doubling the size of the original dataset in the 2D environment with 100 new world configurations and 250,000 tokens. In addition, we propose a new neural architecture that achieves competitive results while automatically discovering an inventory of interpretable spatial operations (Figure 5).

IS Journal 2016 Journal Article

AI's 10 to Watch

• Haris Aziz
• Elias Bareinboim
• Yejin Choi
• Daniel Hsu
• Shivaram Kalyanakrishnan
• Reshef Meir
• Suchi Saria
• Gerardo I. Simari

IEEE Intelligent Systems once again selected 10 young AI scientists as " AI's 10 to Watch. " This acknowledgment and celebration not only recognizes these young scientists and makes a positive impact in their academic career but also promotes the community and cutting-edge AI research among next-generation AI researchers, the industry, and the general public alike. The contributions are "Collective Decision Making in Multi-Agent Systems, " by Haris Aziz, "From Causal Inference and Data Fusion to an Automated Scientist, " by Elias Bareinboim, "Language, Vision, and Social AI, " by Yejin Choi, "Algorithms for Machine Learning, " by Daniel Hsu, "Learning Agents, " by Shivaram Kalyanakrishnan, "Strategy and Bounded Rationality, " by Reshef Meir, "; A Reasoning Engine for Tailoring Healthcare to the Individual, " by Suchi Saria, "Pushing the Limits of Knowledge Representation and Reasoning, " by Gerardo I. Simari, "Better Group Decision Making, " by Lirong Xia, and "Distributed Constraint Optimization, " by William Yeoh.

AAAI Conference 2016 Conference Paper

Are Elephants Bigger than Butterflies? Reasoning about Sizes of Objects

• Hessam Bagherinezhad
• Hannaneh Hajishirzi
• Yejin Choi
• Ali Farhadi

Human vision greatly benefits from the information about sizes of objects. The role of size in several visual reasoning tasks has been thoroughly explored in human perception and cognition. However, the impact of the information about sizes of objects is yet to be determined in AI. We postulate that this is mainly attributed to the lack of a comprehensive repository of size information. In this paper, we introduce a method to automatically infer object sizes, leveraging visual and textual information from web. By maximizing the joint likelihood of textual and visual observations, our method learns reliable relative size estimates, with no explicit human supervision. We introduce the relative size dataset and show that our method outperforms competitive textual and visual baselines in reasoning about size comparisons.

AAAI Conference 2015 Conference Paper

Refer-to-as Relations as Semantic Knowledge

• Song Feng
• Sujith Ravi
• Ravi Kumar
• Polina Kuznetsova
• Wei Liu
• Alexander Berg
• Tamara Berg
• Yejin Choi

We study Refer-to-as relations as a new type of semantic knowledge. Compared to the much studied Is-a relation, which concerns factual taxonomic knowledge, Refer-to-as relations aim to address pragmatic semantic knowledge. For example, a “penguin” is a “bird” from a taxonomic point of view, but people rarely refer to a “penguin” as a “bird” in vernacular use. This observation closely relates to the entry-level categorization studied in Psychology. We posit that Refer-toas relations can be learned from data, and that both textual and visual information would be helpful in inferring the relations. By integrating existing lexical structure knowledge with language statistics and visual similarities, we formulate a collective inference approach to map all object names in an encyclopedia to commonly used names for each object. Our contributions include a new labeled data set, the collective inference and optimization approach, and the computed mappings and similarities.

IJCAI Conference 2007 Conference Paper

• Eric Breck
• Yejin Choi
• Claire Cardie

While traditional information extraction systems have been built to answer questions about facts, subjective information extraction systems will answer questions about feelings and opinions. A crucial step towards this goal is identifying the words and phrases that express opinions in text. Indeed, although much previous work has relied on the identification of opinion expressions for a variety of sentiment-based NLP tasks, none has focused directly on this important supporting task. Moreover, none of the proposed methods for identification of opinion expressions has been evaluated at the task that they were designed to perform. We present an approach for identifying opinion expressions that uses conditional random fields and we evaluate the approach at the expression-level using a standard sentiment corpus. Our approach achieves expression-level performance within 5% of the human interannotator agreement.