Author name cluster

Mrinmaya Sachan

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

26 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

Are Language Models Efficient Reasoners? A Perspective from Logic Programming

Andreas Opedal
Yanick Zengaffinen
Haruki Shirakami
Clemente Pasti
Mrinmaya Sachan
Abulhair Saparov
Ryan Cotterell
Bernhard Schölkopf

Modern language models (LMs) exhibit strong deductive reasoning capabilities, yet standard evaluations emphasize correctness while overlooking a key aspect of reasoning: efficiency. In real-world reasoning scenarios, much of the available information is irrelevant, and effective deductive inference requires identifying and ignoring such distractions. We propose a framework for assessing LM reasoning efficiency through the lens of logic programming, introducing a simple method to align proofs written in natural language---as generated by an LM---with shortest proofs found by executing the logic program. Efficiency is quantified by measuring how well a model avoids unnecessary inference. Empirically, we construct a dataset of math word problems injected with various number of irrelevant axioms that vary in semantic overlap with the goal theorem. We find that current LMs show marked accuracy declines under such conditions---even with minimal, domain-consistent distractions---and the proofs they generate frequently exhibit detours through irrelevant inferences.

PDF Details

AAAI Conference 2025 Conference Paper

Calibrating Large Language Models with Sample Consistency

Qing Lyu
Kumar Shridhar
Chaitanya Malaviya
Li Zhang
Yanai Elazar
Niket Tandon
Marianna Apidianaki
Mrinmaya Sachan

Accurately gauging the confidence level of Large Language Models' (LLMs) predictions is pivotal for their reliable application. However, LLMs are often uncalibrated inherently and elude conventional calibration techniques due to their proprietary nature and massive scale. In this work, we derive model confidence from the distribution of multiple randomly sampled generations, using three measures of consistency. We extensively evaluate eleven open and closed-source models on nine reasoning datasets. Results show that consistency-based calibration methods outperform existing post-hoc approaches in terms of calibration error. Meanwhile, we find that factors such as intermediate explanations, model scaling, and larger sample sizes enhance calibration, while instruction-tuning makes calibration more difficult. Moreover, confidence scores obtained from consistency can potentially enhance model performance. Finally, we offer guidance on choosing suitable consistency metrics for calibration, tailored to model characteristics such as the exposure to instruction-tuning and RLHF.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Dense SAE Latents Are Features, Not Bugs

Xiaoqing Sun
Alessandro Stolfo
Joshua Engels
Ben Wu
Senthooran Rajamanoharan
Mrinmaya Sachan
Max Tegmark

Sparse autoencoders (SAEs) are designed to extract interpretable features from language models by enforcing a sparsity constraint. Ideally, training an SAE would yield latents that are both sparse and semantically meaningful. However, many SAE latents activate frequently (i. e. , are dense ), raising concerns that they may be undesirable artifacts of the training procedure. In this work, we systematically investigate the geometry, function, and origin of dense latents and show that they are not only persistent but often reflect meaningful model representations. We first demonstrate that dense latents tend to form antipodal pairs that reconstruct specific directions in the residual stream, and that ablating their subspace suppresses the emergence of new dense features in retrained SAEs---suggesting that high density features are an intrinsic property of the residual space. We then introduce a taxonomy of dense latents, identifying classes tied to position tracking, context binding, entropy regulation, letter-specific output signals, part-of-speech, and principal component reconstruction. Finally, we analyze how these features evolve across layers, revealing a shift from structural features in early layers, to semantic features in mid layers, and final to output-oriented signals in the last layers of the model. Our findings indicate that dense latents serve functional roles in language model computation and should not be dismissed as training noise.

PDF Details

ICML Conference 2025 Conference Paper

Do Vision-Language Models Really Understand Visual Language?

Yifan Hou
Buse Giledereli
Yilei Tu
Mrinmaya Sachan

Visual language is a system of communication that conveys information through symbols, shapes, and spatial arrangements. Diagrams are a typical example of a visual language depicting complex concepts and their relationships in the form of an image. The symbolic nature of diagrams presents significant challenges for building models capable of understanding them. Yet, recent studies seem to suggest that Large Vision-Language Models (LVLMs) can even tackle complex reasoning tasks involving diagrams. In this paper, we investigate this phenomenon by developing a comprehensive test suite to evaluate the diagram comprehension capability of LVLMs. Our test suite uses a variety of questions focused on concept entities and their relationships over a set of synthetic as well as real diagrams across several domains to evaluate the recognition and reasoning abilities of models. Our evaluation of six LVLMs shows that while these models can accurately identify and reason about entities, their ability to understand relationships is notably limited. Further testing reveals that the decent performance on diagram understanding largely stems from leveraging their background knowledge as shortcuts to identify and reason about the relational information. Thus, we conclude that LVLMs have a limited capability for genuine diagram understanding, and their impressive performance in diagram reasoning is an illusion emanating from other confounding factors, such as the background knowledge in the models.

Details

ICLR Conference 2025 Conference Paper

Language Model Alignment in Multilingual Trolley Problems

Zhijing Jin 0001
Max Kleiman-Weiner
Giorgio Piatti
Sydney Levine
Jiarui Liu 0004
Fernando Gonzalez Adauto
Francesco Ortu
András Strausz

We evaluate the moral alignment of large language models (LLMs) with human preferences in multilingual trolley problems. Building on the Moral Machine experiment, which captures over 40 million human judgments across 200+ countries, we develop a cross-lingual corpus of moral dilemma vignettes in over 100 languages called MultiTP. This dataset enables the assessment of LLMs' decision-making processes in diverse linguistic contexts. Our analysis explores the alignment of 19 different LLMs with human judgments, capturing preferences across six moral dimensions: species, gender, fitness, status, age, and the number of lives involved. By correlating these preferences with the demographic distribution of language speakers and examining the consistency of LLM responses to various prompt paraphrasings, our findings provide insights into cross-lingual and ethical biases of LLMs and their intersection. We discover significant variance in alignment across languages, challenging the assumption of uniform moral reasoning in AI systems and highlighting the importance of incorporating diverse perspectives in AI ethics. The results underscore the need for further research on the integration of multilingual dimensions in responsible AI research to ensure fair and equitable AI interactions worldwide.

Details

ICLR Conference 2025 Conference Paper

MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs

Andreas Opedal
Haruki Shirakami
Bernhard Schölkopf
Abulhair Saparov
Mrinmaya Sachan

Large language models (LLMs) can solve arithmetic word problems with high accuracy, but little is known about how well they generalize to more complex problems. This is difficult to study, as (i) much of the available evaluation data has already been seen by the most capable models during training, and (ii) existing benchmarks do not capture how problem proofs may be arbitrarily complex in various ways. In this paper, we present a data-generation framework for evaluating LLMs on problems with arbitrarily complex arithmetic proofs, called MathGAP. MathGAP generates problem statements and chain-of-thought reasoning traces according to specifications about their arithmetic proof structure, enabling systematic studies on easy-to-hard generalization with respect to complexity of proof trees. Using MathGAP, we find that LLMs show a significant decrease in performance as proofs get deeper and wider. This effect is more pronounced in complex, nonlinear proof structures, which are challenging even for the most capable models. The models are also sensitive to simple changes in sentence ordering. However, they remain capable of solving some complex problems, suggesting that reasoning generalization is noisy.

Details

NeurIPS Conference 2025 Conference Paper

Personalized Exercise Recommendation with Semantically-Grounded Knowledge Tracing

Yilmazcan Ozyurt
Tunaberk Almaci
Stefan Feuerriegel
Mrinmaya Sachan

We introduce ExRec, a general framework for personalized exercise recommendation with semantically-grounded knowledge tracing. Our method builds on the observation that existing exercise recommendation approaches simulate student performance via knowledge tracing (KT) but they often overlook two key aspects: (a) the semantic content of questions and (b) the sequential, structured progression of student learning. To address this, our ExRec presents an end-to-end pipeline, from annotating the KCs of questions and learning their semantic representations to training KT models and optimizing several reinforcement learning (RL) methods. Moreover, we improve standard Q-learning-based continuous RL methods via a tailored model-based value estimation (MVE) approach that directly leverages the components of KT model in estimating cumulative knowledge improvement. We validate the effectiveness of our ExRec using various RL methods across four real-world tasks with different educational goals in online math learning. We further show that ExRec generalizes robustly to new, unseen questions and that it produces interpretable student learning trajectories. Together, our findings highlight the promise of KT-guided RL for effective personalization in education.

PDF Details

NeurIPS Conference 2025 Conference Paper

SeePhys: Does Seeing Help Thinking? – Benchmarking Vision-Based Physics Reasoning

Kun Xiang
Heng Li
Terry Jingchen Zhang
Yinya Huang
Zirong Liu
Peixin Qu
Jixi He
Jiaqi Chen

We present SeePhys, a large-scale multimodal benchmark for LLM reasoning grounded in physics questions ranging from middle school to PhD qualifying exams. The benchmark covers 7 fundamental domains spanning the physics discipline, incorporating 21 categories of highly heterogeneous diagrams. In contrast to prior works where visual elements mainly serve auxiliary purposes, our benchmark features a substantial proportion of vision-essential problems (75%) that mandate visual information extraction for correct solutions. Through extensive evaluation, we observe that even the most advanced visual reasoning models (e. g. , Gemini-2. 5-pro and o4-mini) achieve sub-60% accuracy on our benchmark. These results reveal fundamental challenges in current large language models' visual understanding capabilities, particularly in: (i) establishing rigorous coupling between diagram interpretation and physics reasoning, and (ii) overcoming their persistent reliance on textual cues as cognitive shortcuts. Project Page: github. com/SeePhys/seephys-projectHugging Face: huggingface. co/datasets/SeePhys/SeePhys

PDF Details

ICLR Conference 2024 Conference Paper

Can Large Language Models Infer Causation from Correlation?

Zhijing Jin 0001
Jiarui Liu 0004
Zhiheng Lyu
Spencer Poff
Mrinmaya Sachan
Rada Mihalcea
Mona T. Diab
Bernhard Schölkopf

Causal inference is one of the hallmarks of human intelligence. While the field of CausalNLP has attracted much interest in the recent years, existing causal inference datasets in NLP primarily rely on discovering causality from empirical knowledge (e.g., commonsense knowledge). In this work, we propose the first benchmark dataset to test the pure causal inference skills of large language models (LLMs). Specifically, we formulate a novel task Corr2Cause, which takes a set of correlational statements and determines the causal relationship between the variables. We curate a large-scale dataset of more than 200K samples, on which we evaluate seventeen existing LLMs. Through our experiments, we identify a key shortcoming of LLMs in terms of their causal inference skills, and show that these models achieve almost close to random performance on the task. This shortcoming is somewhat mitigated when we try to re-purpose LLMs for this skill via finetuning, but we find that these models still fail to generalize – they can only perform causal inference in in-distribution settings when variable names and textual expressions used in the queries are similar to those in the training set, but fail in out-of-distribution settings generated by perturbing these queries. Corr2Cause is a challenging task for LLMs, and can be helpful in guiding future research on improving LLMs’ pure reasoning skills and generalizability. Our data is at https://huggingface.co/datasets/causalnlp/corr2cause. Our code is at https://github.com/causalNLP/corr2cause.

Details

NeurIPS Conference 2024 Conference Paper

Confidence Regulation Neurons in Language Models

Alessandro Stolfo
Ben Wu
Wes Gurnee
Yonatan Belinkov
Xingyi Song
Mrinmaya Sachan
Neel Nanda

Despite their widespread use, the mechanisms by which large language models (LLMs) represent and regulate uncertainty in next-token predictions remain largely unexplored. This study investigates two critical components believed to influence this uncertainty: the recently discovered entropy neurons and a new set of components that we term token frequency neurons. Entropy neurons are characterized by an unusually high weight norm and influence the final layer normalization (LayerNorm) scale to effectively scale down the logits. Our work shows that entropy neurons operate by writing onto an \textit{unembedding null space}, allowing them to impact the residual stream norm with minimal direct effect on the logits themselves. We observe the presence of entropy neurons across a range of models, up to 7 billion parameters. On the other hand, token frequency neurons, which we discover and describe here for the first time, boost or suppress each token’s logit proportionally to its log frequency, thereby shifting the output distribution towards or away from the unigram distribution. Finally, we present a detailed case study where entropy neurons actively manage confidence: the setting of induction, i. e. detecting and continuing repeated subsequences.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents

Giorgio Piatti
Zhijing Jin
Max Kleiman-Weiner
Bernhard Schölkopf
Mrinmaya Sachan
Rada Mihalcea

As AI systems pervade human life, ensuring that large language models (LLMs) make safe decisions remains a significant challenge. We introduce the Governance of the Commons Simulation (GovSim), a generative simulation platform designed to study strategic interactions and cooperative decision-making in LLMs. In GovSim, a society of AI agents must collectively balance exploiting a common resource with sustaining it for future use. This environment enables the study of how ethical considerations, strategic planning, and negotiation skills impact cooperative outcomes. We develop an LLM-based agent architecture and test it with the leading open and closed LLMs. We find that all but the most powerful LLM agents fail to achieve a sustainable equilibrium in GovSim, with the highest survival rate below 54%. Ablations reveal that successful multi-agent communication between agents is critical for achieving cooperation in these cases. Furthermore, our analyses show that the failure to achieve sustainable cooperation in most LLMs stems from their inability to formulate and analyze hypotheses about the long-term effects of their actions on the equilibrium of the group. Finally, we show that agents that leverage "Universalization"-based reasoning, a theory of moral thinking, are able to achieve significantly better sustainability. Taken together, GovSim enables us to study the mechanisms that underlie sustainable self-government with specificity and scale. We open source the full suite of our research results, including the simulation environment, agent prompts, and a comprehensive web interface.

PDF Details DOI

ICML Conference 2024 Conference Paper

Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?

Andreas Opedal
Alessandro Stolfo
Haruki Shirakami
Ying Jiao
Ryan Cotterell
Bernhard Schölkopf
Abulhair Saparov
Mrinmaya Sachan

There is increasing interest in employing large language models (LLMs) as cognitive models. For such purposes, it is central to understand which properties of human cognition are well-modeled by LLMs, and which are not. In this work, we study the biases of LLMs in relation to those known in children when solving arithmetic word problems. Surveying the learning science literature, we posit that the problem-solving process can be split into three distinct steps: text comprehension, solution planning and solution execution. We construct tests for each one in order to understand whether current LLMs display the same cognitive biases as children in these steps. We generate a novel set of word problems for each of these tests, using a neuro-symbolic approach that enables fine-grained control over the problem features. We find evidence that LLMs, with and without instruction-tuning, exhibit human-like biases in both the text-comprehension and the solution-planning steps of the solving process, but not in the final step, in which the arithmetic expressions are executed to obtain the answer.

Details

NeurIPS Conference 2024 Conference Paper

On Affine Homotopy between Language Encoders

Robin S. Chan
Reda Boumasmoud
Anej Svete
Yuxin Ren
Qipeng Guo
Zhijing Jin
Shauli Ravfogel
Mrinmaya Sachan

Pre-trained language encoders---functions that represent text as vectors---are an integral component of many NLP tasks. We tackle a natural question in language encoder analysis: What does it mean for two encoders to be similar? We contend that a faithful measure of similarity needs to be \emph{intrinsic}, that is, task-independent, yet still be informative of \emph{extrinsic} similarity---the performance on downstream tasks. It is common to consider two encoders similar if they are \emph{homotopic}, i. e. , if they can be aligned through some transformation. In this spirit, we study the properties of \emph{affine} alignment of language encoders and its implications on extrinsic similarity. We find that while affine alignment is fundamentally an asymmetric notion of similarity, it is still informative of extrinsic similarity. We confirm this on datasets of natural language representations. Beyond providing useful bounds on extrinsic similarity, affine intrinsic similarity also allows us to begin uncovering the structure of the space of pre-trained encoders by defining an order over them.

PDF Details DOI

ECAI Conference 2024 Conference Paper

RETRO-LI: Small-Scale Retrieval Augmented Generation Supporting Noisy Similarity Searches and Domain Shift Generalization

Gentiana Rashiti
Geethan Karunaratne
Mrinmaya Sachan
Abu Sebastian
Abbas Rahimi

The retrieval augmented generation (RAG) system such as RETRO has been shown to improve language modeling capabilities and reduce toxicity and hallucinations by retrieving from a database of non-parametric memory containing trillions of entries. We introduce RETRO-LI that shows retrieval can also help using a small scale database, but it demands more accurate and better neighbors when searching in a smaller hence sparser non-parametric memory. This can be met by using a proper semantic similarity search. We further propose adding a regularization to the non-parametric memory for the first time: it significantly reduces perplexity when the neighbor search operations are noisy during inference, and it improves generalization when a domain shift occurs. We also show that the RETRO-LI’s non-parametric memory can potentially be implemented on analog in-memory computing hardware, exhibiting O(1) search time while causing noise in retrieving neighbors, with minimal (<1%) performance loss. Our code is available at: https: //github. com/IBM/Retrieval-Enhanced-Transformer-Little

Details

TMLR Journal 2024 Journal Article

Variational Classification: A Probabilistic Generalization of the Softmax Classifier

Shehzaad Zuzar Dhuliawala
Mrinmaya Sachan
Carl Allen

We present a latent variable model for classification that provides a novel probabilistic interpretation of neural network softmax classifiers. We derive a variational objective to train the model, analogous to the evidence lower bound (ELBO) used to train variational auto-encoders, that generalises the cross-entropy loss used to train classification models. Treating inputs to the softmax layer as samples of a latent variable, our abstracted perspective reveals a potential inconsistency between their anticipated distribution, required for accurate label predictions to be output, and the empirical distribution found in practice. We augment the variational objective to mitigate such inconsistency and encourage a chosen latent distribution, instead of the implicit assumption in off-the-shelf softmax classifiers. Overall, we provide new theoretical insight into the inner workings of widely-used softmax classification. Empirical evaluation on image and text classification datasets demonstrates that our proposed approach, variational classification, maintains classification accuracy while the reshaped latent space improves other desirable properties of a classifier, such as calibration, adversarial robustness, robustness to distribution shift and sample efficiency useful in low data settings.

PDF Details

NeurIPS Conference 2023 Conference Paper

CLadder: Assessing Causal Reasoning in Language Models

Zhijing Jin
Yuen Chen
Felix Leeb
Luigi Gresele
Ojasv Kamal
Zhiheng Lyu
Kevin Blin
Fernando Gonzalez Adauto

The ability to perform causal reasoning is widely considered a core feature of intelligence. In this work, we investigate whether large language models (LLMs) can coherently reason about causality. Much of the existing work in natural language processing (NLP) focuses on evaluating commonsense causal reasoning in LLMs, thus failing to assess whether a model can perform causal inference in accordance with a set of well-defined formal rules. To address this, we propose a new NLP task, causal inference in natural language, inspired by the "causal inference engine" postulated by Judea Pearl et al. We compose a large dataset, CLadder, with 10K samples: based on a collection of causal graphs and queries (associational, interventional, and counterfactual), we obtain symbolic questions and ground-truth answers, through an oracle causal inference engine. These are then translated into natural language. We evaluate multiple LLMs on our dataset, and we introduce and evaluate a bespoke chain-of-thought prompting strategy, CausalCoT. We show that our task is highly challenging for LLMs, and we conduct an in-depth analysis to gain deeper insight into the causal reasoning abilities of LLMs. Our data is open-sourced at https: //huggingface. co/datasets/causalNLP/cladder, and our code can be found at https: //github. com/causalNLP/cladder.

PDF Details

ICML Conference 2023 Conference Paper

Controlled Text Generation with Natural Language Instructions

Wangchunshu Zhou
Yuchen Eleanor Jiang
Ethan Wilcox
Ryan Cotterell
Mrinmaya Sachan

Large language models can be prompted to pro- duce fluent output for a wide range of tasks without being specifically trained to do so. Nevertheless, it is notoriously difficult to control their generation in such a way that it satisfies user-specified constraints. In this paper, we present InstructCTG, a simple controlled text generation framework that incorporates different constraints by verbalizing them as natural language instructions. We annotate natural texts through a combination of off-the-shelf NLP tools and simple heuristics with the linguistic and extra-linguistic constraints they satisfy. Then, we verbalize the constraints into natural language instructions to form weakly supervised training data, i. e. , we prepend the natural language verbalizations of the constraints in front of their corresponding natural language sentences. Next, we fine-tune a pre-trained language model on the augmented corpus. Compared to existing methods, InstructCTG is more flexible in terms of the types of constraints it allows the practitioner to use. It also does not require any modification of the decoding procedure. Finally, InstructCTG allows the model to adapt to new constraints without re-training through the use of in-context learning.

Details

ICML Conference 2023 Conference Paper

Infusing Lattice Symmetry Priors in Attention Mechanisms for Sample-Efficient Abstract Geometric Reasoning

Mattia Atzeni
Mrinmaya Sachan
Andreas Loukas

The Abstraction and Reasoning Corpus (ARC) (Chollet, 2019) and its most recent language-complete instantiation (LARC) has been postulated as an important step towards general AI. Yet, even state-of-the-art machine learning models struggle to achieve meaningful performance on these problems, falling behind non-learning based approaches. We argue that solving these tasks requires extreme generalization that can only be achieved by proper accounting for core knowledge priors. As a step towards this goal, we focus on geometry priors and introduce LatFormer, a model that incorporates lattice symmetry priors in attention masks. We show that, for any transformation of the hypercubic lattice, there exists a binary attention mask that implements that group action. Hence, our study motivates a modification to the standard attention mechanism, where attention weights are scaled using soft masks generated by a convolutional network. Experiments on synthetic geometric reasoning show that LatFormer requires 2 orders of magnitude fewer data than standard attention and transformers. Moreover, our results on ARC and LARC tasks that incorporate geometric priors provide preliminary evidence that these complex datasets do not lie out of the reach of deep learning models.

Details

ICLR Conference 2022 Conference Paper

Case-based reasoning for better generalization in textual reinforcement learning

Mattia Atzeni
Shehzaad Zuzar Dhuliawala
Keerthiram Murugesan
Mrinmaya Sachan

Text-based games (TBG) have emerged as promising environments for driving research in grounded language understanding and studying problems like generalization and sample efficiency. Several deep reinforcement learning (RL) methods with varying architectures and learning schemes have been proposed for TBGs. However, these methods fail to generalize efficiently, especially under distributional shifts. In a departure from deep RL approaches, in this paper, we propose a general method inspired by case-based reasoning to train agents and generalize out of the training distribution. The case-based reasoner collects instances of positive experiences from the agent's interaction with the world and later reuses the collected experiences to act efficiently. The method can be used in conjunction with any existing on-policy neural agent introduced in the literature for TBGs. Our experiments show that the proposed approach consistently improves existing methods, obtains good out-of-distribution generalization and achieves new state-of-the-art results on widely used environments.

Details

AAAI Conference 2022 Conference Paper

Deep Clustering of Text Representations for Supervision-Free Probing of Syntax

Vikram Gupta
Haoyue Shi
Kevin Gimpel
Mrinmaya Sachan

We explore deep clustering of text representations for unsupervised model interpretation and induction of syntax. As these representations are high-dimensional, out-of-the-box methods like KMeans do not work well. Thus, our approach jointly transforms the representations into a lowerdimensional cluster-friendly space and clusters them. We consider two notions of syntax: part of speech induction (POSI) and constituency labelling (CoLab) in this work. Interestingly, we find that Multilingual BERT (mBERT) contains surprising amount of syntactic knowledge of English; possibly even as much as English BERT (E-BERT). Our model can be used as a supervision-free probe which is arguably a less-biased way of probing. We find that unsupervised probes show benefits from higher layers as compared to supervised probes. We further note that our unsupervised probe utilizes E-BERT and mBERT representations differently, especially for POSI. We validate the efficacy of our probe by demonstrating its capabilities as a unsupervised syntax induction technique. Our probe works well for both syntactic formalisms by simply adapting the input representations. We report competitive performance of our probe on 45-tag English POSI, state-of-the-art performance on 12tag POSI across 10 languages, and competitive results on CoLab. We also perform zero-shot syntax induction on resource impoverished languages and report strong results.

PDF Details

TMLR Journal 2022 Journal Article

Learning the Transformer Kernel

Sankalan Pal Chowdhury
Adamos Solomou
Kumar Avinava Dubey
Mrinmaya Sachan

In this work we introduce KL-TRANSFORMER, a generic, scalable, data driven framework for learning the kernel function in Transformers. Our framework approximates the Transformer kernel as a dot product between spectral feature maps and learns the kernel by learning the spectral distribution. This not only helps in learning a generic kernel end-to-end, but also reduces the time and space complexity of Transformers from quadratic to linear. We show that KL-TRANSFORMERs achieve performance comparable to existing efficient Transformer architectures, both in terms of accuracy and computational efficiency. Our study also demonstrates that the choice of the kernel has a substantial impact on performance, and kernel learning variants are competitive alternatives to fixed kernel Transformers, both in long as well as short sequence tasks.

PDF Details

NeurIPS Conference 2022 Conference Paper

When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment

Zhijing Jin
Sydney Levine
Fernando Gonzalez Adauto
Ojasv Kamal
Maarten Sap
Mrinmaya Sachan
Rada Mihalcea
Josh Tenenbaum

AI systems are becoming increasingly intertwined with human life. In order to effectively collaborate with humans and ensure safety, AI systems need to be able to understand, interpret and predict human moral judgments and decisions. Human moral judgments are often guided by rules, but not always. A central challenge for AI safety is capturing the flexibility of the human moral mind — the ability to determine when a rule should be broken, especially in novel or unusual situations. In this paper, we present a novel challenge set consisting of moral exception question answering (MoralExceptQA) of cases that involve potentially permissible moral exceptions – inspired by recent moral psychology studies. Using a state-of-the-art large language model (LLM) as a basis, we propose a novel moral chain of thought (MoralCoT) prompting strategy that combines the strengths of LLMs with theories of moral reasoning developed in cognitive science to predict human moral judgments. MoralCoT outperforms seven existing LLMs by 6. 2% F1, suggesting that modeling human reasoning might be necessary to capture the flexibility of the human moral mind. We also conduct a detailed error analysis to suggest directions for future work to improve AI safety using MoralExceptQA. Our data is open-sourced at https: //huggingface. co/datasets/feradauto/MoralExceptQA and code at https: //github. com/feradauto/MoralCoT.

PDF Details

AAAI Conference 2021 Conference Paper

Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines

Keerthiram Murugesan
Mattia Atzeni
Pavan Kapanipathi
Pushkar Shukla
Sadhana Kumaravel
Gerald Tesauro
Kartik Talamadupula
Mrinmaya Sachan

Text-based games have emerged as an important test-bed for Reinforcement Learning (RL) research, requiring RL agents to combine grounded language understanding with sequential decision making. In this paper, we examine the problem of infusing RL agents with commonsense knowledge. Such knowledge would allow agents to efficiently act in the world by pruning out implausible actions, and to perform lookahead planning to determine how current actions might affect future world states. We design a new text-based gaming environment called TextWorld Commonsense (TWC) for training and evaluating RL agents with a specific kind of commonsense knowledge about objects, their attributes, and affordances. We also introduce several baseline RL agents which track the sequential context and dynamically retrieve the relevant commonsense knowledge from ConceptNet. We show that agents which incorporate commonsense knowledge in TWC perform better, while acting more efficiently. We conduct user-studies to estimate human performance on TWC and show that there is ample room for future improvement.

PDF Details

NeurIPS Conference 2018 Conference Paper

Learning Pipelines with Limited Data and Domain Knowledge: A Study in Parsing Physics Problems

Mrinmaya Sachan
Kumar Avinava Dubey
Tom Mitchell
Dan Roth
Eric Xing

As machine learning becomes more widely used in practice, we need new methods to build complex intelligent systems that integrate learning with existing software, and with domain knowledge encoded as rules. As a case study, we present such a system that learns to parse Newtonian physics problems in textbooks. This system, Nuts&Bolts, learns a pipeline process that incorporates existing code, pre-learned machine learning models, and human engineered rules. It jointly trains the entire pipeline to prevent propagation of errors, using a combination of labelled and unlabelled data. Our approach achieves a good performance on the parsing task, outperforming the simple pipeline and its variants. Finally, we also show how Nuts&Bolts can be used to achieve improvements on a relation extraction task and on the end task of answering Newtonian physics problems.

PDF Details

IJCAI Conference 2016 Conference Paper

Grounding Topic Models with Knowledge Bases

Zhiting Hu
Gang Luo
Mrinmaya Sachan
Eric Xing
Zaiqing Nie

Topic models represent latent topics as probability distributions over words which can be hard to interpret due to the lack of grounded semantics. In this paper, we propose a structured topic representation based on an entity taxonomy from a knowledge base. A probabilistic model is developed to infer both hidden topics and entities from text corpora. Each topic is equipped with a random walk over the entity hierarchy to extract semantically grounded and coherent themes. Accurate entity modeling is achieved by leveraging rich textual features from the knowledge base. Experiments show significant superiority of our approach in topic perplexity and key entity identification, indicating potentials of the grounded modeling for semantic extraction and language understanding applications.

PDF Details

IJCAI Conference 2015 Conference Paper

An Active Learning Approach to Coreference Resolution

Mrinmaya Sachan
Eduard Hovy
Eric P. Xing

In this paper, we define the problem of coreference resolution in text as one of clustering with pairwise constraints where human experts are asked to provide pairwise constraints (pairwise judgments of coreferentiality) to guide the clustering process. Positing that these pairwise judgments are easy to obtain from humans given the right context, we show that with significantly lower number of pairwise judgments and feature-engineering effort, we can achieve competitive coreference performance. Further, we describe an active learning strategy that minimizes the overall number of such pairwise judgments needed by asking the most informative questions to human experts at each step of coreference resolution. We evaluate this hypothesis and our algorithms on both entity and event coreference tasks and on two languages.

PDF Details