Author name cluster

Samuel R. Bowman

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.

11 papers

2 author rows

ICLR Conference 2025 Conference Paper

Language Models Learn to Mislead Humans via RLHF

Jiaxin Wen
Ruiqi Zhong
Akbir Khan
Ethan Perez
Jacob Steinhardt
Minlie Huang
Samuel R. Bowman
He He 0001

Language models (LMs) can produce errors that are hard to detect for humans, especially when the task is complex. RLHF, the most popular post-training method, may exacerbate this problem: to achieve higher rewards, LMs might get better at convincing humans that they are right even when they are wrong. We study this phenomenon under a standard RLHF pipeline, calling it ``U-Sophistry'' since it is \textbf{U}nintended by model developers. Specifically, we ask time-constrained (e.g., 3-10 minutes) human subjects to evaluate the correctness of model outputs and calculate humans' accuracy against gold labels. On a question-answering task (QuALITY) and programming task (APPS), RLHF makes LMs better at convincing our subjects but not at completing the task correctly. RLHF also makes the model harder to evaluate: our subjects' false positive rate increases by 24.1% on QuALITY and 18.3% on APPS. Finally, we show that probing, a state-of-the-art approach for detecting \textbf{I}ntended Sophistry (e.g.~backdoored LMs), does not generalize to U-Sophistry. Our results highlight an important failure mode of RLHF and call for more research in assisting humans to align them.

Details

ICML Conference 2024 Conference Paper

Debating with More Persuasive LLMs Leads to More Truthful Answers

Akbir Khan
John Hughes
Dan Valentine
Laura Ruis
Kshitij Sachan
Ansh Radhakrishnan
Edward Grefenstette
Samuel R. Bowman

Common methods for aligning large language models (LLMs) with desired behaviour heavily rely on human-labelled data. However, as models grow increasingly sophisticated, they will surpass human expertise, and the role of human evaluation will evolve into non-experts overseeing experts. In anticipation of this, we ask: can weaker models assess the correctness of stronger models? We investigate this question in an analogous setting, where stronger models (experts) possess the necessary information to answer questions and weaker models (non-experts) lack this information. The method we evaluate is debate, where two LLM experts each argue for a different answer, and a non-expert selects the answer. We find that debate consistently helps both non-expert models and humans answer questions, achieving 76% and 88% accuracy respectively (naive baselines obtain 48% and 60%). Furthermore, optimising expert debaters for persuasiveness in an unsupervised manner improves non-expert ability to identify the truth in debates. Our results provide encouraging empirical evidence for the viability of aligning models with debate in the absence of ground truth.

Details

TMLR Journal 2024 Journal Article

Learning from Natural Language Feedback

Angelica Chen
Jérémy Scheurer
Jon Ander Campos
Tomasz Korbak
Jun Shern Chan
Samuel R. Bowman
Kyunghyun Cho
Ethan Perez

The potential for pre-trained large language models (LLMs) to use natural language feedback at inference time has been an exciting recent development. We build upon this observation by formalizing an algorithm for learning from natural language feedback at training time instead, which we call Imitation learning from Language Feedback (ILF). ILF requires only a small amount of human-written feedback during training and does not require the same feedback at test time, making it both user-friendly and sample-efficient. We further show that ILF can be seen as a form of minimizing the KL divergence to the target distribution and demonstrate proof-of-concepts on text summarization and program synthesis tasks. For code generation, ILF improves a Codegen-Mono 6.1B model's pass@1 rate by 38% relative (and 10% absolute) on the Mostly Basic Python Problems (MBPP) benchmark, outperforming both fine-tuning on MBPP and fine-tuning on repaired programs written by humans. For summarization, we show that ILF can be combined with learning from human preferences to improve a GPT-3 model's summarization performance to be comparable to human quality, outperforming fine-tuning on human-written summaries. Overall, our results suggest that learning from human-written natural language feedback is both more effective and sample-efficient than training exclusively on demonstrations for improving an LLM's performance on a variety of tasks.

PDF Details

NeurIPS Conference 2024 Conference Paper

LLM Evaluators Recognize and Favor Their Own Generations

Arjun Panickssery
Samuel R. Bowman
Shi Feng

Self-evaluation using large language models (LLMs) has proven valuable not only in benchmarking but also methods like reward modeling, constitutional AI, and self-refinement. But new biases are introduced due to the same LLM acting as both the evaluator and the evaluatee. One such bias is self-preference, where an LLM evaluator scores its own outputs higher than others’ while human annotators consider them of equal quality. But do LLMs actually recognize their own outputs when they give those texts higher scores, or is it just a coincidence? In this paper, we investigate if self-recognition capability contributes to self-preference. We discover that, out of the box, LLMs such as GPT-4 and Llama 2 have non-trivial accuracy at distinguishing themselves from other LLMs and humans. By finetuning LLMs, we discover a linear correlation between self-recognition capability and the strength of self-preference bias; using controlled experiments, we show that the causal explanation resists straightforward confounders. We discuss how self-recognition can interfere with unbiased evaluations and AI safety more generally.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Many-shot Jailbreaking

Cem Anil
Esin Durmus
Nina Panickssery
Mrinank Sharma
Joe Benton
Sandipan Kundu
Joshua Batson
Meg Tong

We investigate a family of simple long-context attacks on large language models: prompting with hundreds of demonstrations of undesirable behavior. This attack is newly feasible with the larger context windows recently deployed by language model providers like Google DeepMind, OpenAI and Anthropic. We find that in diverse, realistic circumstances, the effectiveness of this attack follows a power law, up to hundreds of shots. We demonstrate the success of this attack on the most widely used state-of-the-art closed-weight models, and across various tasks. Our results suggest very long contexts present a rich new attack surface for LLMs.

PDF Details DOI

ICLR Conference 2024 Conference Paper

Towards Understanding Sycophancy in Language Models

Mrinank Sharma
Meg Tong
Tomasz Korbak
David Duvenaud
Amanda Askell
Samuel R. Bowman
Esin Durmus
Zac Hatfield-Dodds

Reinforcement learning from human feedback (RLHF) is a popular technique for training high-quality AI assistants. However, RLHF may also encourage model responses that match user beliefs over truthful responses, a behavior known as sycophancy. We investigate the prevalence of sycophancy in RLHF-trained models and whether human preference judgments are responsible. We first demonstrate that five state-of-the-art AI assistants consistently exhibit sycophancy behavior across four varied free-form text-generation tasks. To understand if human preferences drive this broadly observed behavior of RLHF models, we analyze existing human preference data. We find that when a response matches a user's views, it is more likely to be preferred. Moreover, both humans and preference models (PMs) prefer convincingly-written sycophantic responses over correct ones a non-negligible fraction of the time. Optimizing model outputs against PMs also sometimes sacrifices truthfulness in favor of sycophancy. Overall, our results indicate that sycophancy is a general behavior of RLHF models, likely driven in part by human preference judgments favoring sycophantic responses.

Details

TMLR Journal 2024 Journal Article

Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs

Angelica Chen
Jason Phang
Alicia Parrish
Vishakh Padmakumar
Chen Zhao
Samuel R. Bowman
Kyunghyun Cho

Large language models (LLMs) have achieved widespread success on a variety of in-context few-shot tasks, but this success is typically evaluated via correctness rather than consistency. We argue that self-consistency is an important criteria for valid multi-step reasoning in tasks where the solution is composed of the answers to multiple sub-steps. We propose two types of self-consistency that are particularly important for multi-step reasoning -- hypothetical consistency (a model's ability to predict what its output would be in a hypothetical other context) and compositional consistency (consistency of a model's final outputs when intermediate sub-steps are replaced with the model's outputs for those steps). We demonstrate that multiple variants of the GPT-3/-4 models exhibit poor consistency rates across both types of consistency on a variety of tasks.

PDF Details

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.

PDF Details

TMLR Journal 2023 Journal Article

Inverse Scaling: When Bigger Isn't Better

Ian R. McKenzie
Alexander Lyzhov
Michael Martin Pieler
Alicia Parrish
Aaron Mueller
Ameya Prabhu
Euan McLean
Xudong Shen

Work on scaling laws has found that large language models (LMs) show predictable improvements to overall loss with increased scale (model size, training data, and compute). Here, we present evidence for the claim that LMs may show inverse scaling, or worse task performance with increased scale, e.g., due to flaws in the training objective and data. We present empirical evidence of inverse scaling on 11 datasets collected by running a public contest, the Inverse Scaling Prize, with a substantial prize pool. Through analysis of the datasets, along with other examples found in the literature, we identify four potential causes of inverse scaling: (i) preference to repeat memorized sequences over following in-context instructions, (ii) imitation of undesirable patterns in the training data, (iii) tasks containing an easy distractor task which LMs could focus on, rather than the harder real task, and (iv) correct but misleading few-shot demonstrations of the task. We release the winning datasets at inversescaling.com/data to allow for further investigation of inverse scaling. Our tasks have helped drive the discovery of U-shaped and inverted-U scaling trends, where an initial trend reverses, suggesting that scaling trends are less reliable at predicting the behavior of larger-scale models than previously understood. Overall, our results suggest that there are tasks for which increased model scale alone may not lead to progress, and that more careful thought needs to go into the data and objectives for training language models.

PDF Details

ICML Conference 2023 Conference Paper

Pretraining Language Models with Human Preferences

Tomasz Korbak
Kejian Shi
Angelica Chen
Rasika Vinayak Bhalerao
Christopher L. Buckley
Jason Phang
Samuel R. Bowman
Ethan Perez

Language models (LMs) are pretrained to imitate text from large and diverse datasets that contain content that would violate human preferences if generated by an LM: falsehoods, offensive comments, personally identifiable information, low-quality or buggy code, among others. Here, we explore alternative objectives for pretraining LMs in a way that also guides them to generate text aligned with human preferences. We benchmark five objectives for pretraining with human feedback across three tasks and study how they affect the alignment and capabilities of pretrained LMs. We find a Pareto-optimal and simple approach among those we explored: conditional training, or learning distribution over tokens conditional on their human preference scores. Conditional training reduces the rate of undesirable content by up to an order of magnitude, both when generating without a prompt and with an adversarially-chosen prompt. Moreover, conditional training maintains the downstream task performance of standard LM pretraining, both before and after task-specific finetuning. Pretraining with human feedback results in much better preference satisfaction than standard LM pretraining followed by finetuning with feedback, i. e. , learning and then unlearning undesirable behavior. Our results suggest that we should move beyond imitation learning when pretraining LMs and incorporate human preferences from the start of training.

Details

AAAI Conference 2020 Conference Paper

Learning to Learn Morphological Inflection for Resource-Poor Languages

Katharina Kann
Samuel R. Bowman
Kyunghyun Cho

We propose to cast the task of morphological inﬂection— mapping a lemma to an indicated inﬂected form—for resource-poor languages as a meta-learning problem. Treating each language as a separate task, we use data from highresource source languages to learn a set of model parameters that can serve as a strong initialization point for ﬁne-tuning on a resource-poor target language. Experiments with two model architectures on 29 target languages from 3 families show that our suggested approach outperforms all baselines. In particular, it obtains a 31. 7% higher absolute accuracy than a previously proposed cross-lingual transfer model and outperforms the previous state of the art by 1. 7% absolute accuracy on average over languages.

PDF Details