papers

Publications (273)

cs.AI2025

BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments

Yusuf Roohani, Andrew Lee, Qian Huang +6

Agents based on large language models have shown great potential in accelerating scientific discovery by leveraging their rich background knowledge and reasoning capabilities. In t…

cs.CL2019

Unifying Human and Statistical Evaluation for Natural Language Generation

Tatsunori B. Hashimoto, Hugh Zhang, Percy Liang

How can we measure whether a natural language generation system produces both high quality and diverse outputs? Human evaluation captures quality but not diversity, as it does not…

math.ST2014

The Statistics of Streaming Sparse Regression

Jacob Steinhardt, Stefan Wager, Percy Liang

We present a sparse analogue to stochastic gradient descent that is guaranteed to perform well under similar conditions to the lasso. In the linear regression setup with irrepresen…

cs.CL2026

The Mighty ToRR: A Benchmark for Table Reasoning and Robustness

Shir Ashury-Tahan, Yifan Mai, Rajmohan C +8

Despite its real-world significance, model performance on tabular data remains underexplored, leaving uncertainty about which model to rely on and which prompt configuration to ado…

cs.CY2025

The California Report on Frontier AI Policy

Rishi Bommasani, Scott R. Singer, Ruth E. Appel +20

The innovations emerging at the frontier of artificial intelligence (AI) are poised to create historic opportunities for humanity but also raise complex policy challenges. Continue…

cs.LG2025

Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators

Yann Dubois, Balázs Galambosi, Percy Liang +1

LLM-based auto-annotators have become a key component of the LLM development process due to their cost-effectiveness and scalability compared to human-based evaluation. However, th…

cs.CL2025

Language Models May Verbatim Complete Text They Were Not Explicitly Trained On

Ken Ziyu Liu, Christopher A. Choquette-Choo, Matthew Jagielski +4

An important question today is whether a given text was used to train a large language model (LLM). A \emph{completion} test is often employed: check if the LLM completes a suffici…

cs.RO2024

OpenVLA: An Open-Source Vision-Language-Action Model

Moo Jin Kim, Karl Pertsch, Siddharth Karamcheti +15

Large policies pretrained on a combination of Internet-scale vision-language data and diverse robot demonstrations have the potential to change how we teach robots new skills: rath…

cs.RO2025

RoboArena: Distributed Real-World Evaluation of Generalist Robot Policies

Pranav Atreya, Karl Pertsch, Tony Lee +29

Comprehensive, unbiased, and comparable evaluation of modern generalist policies is uniquely challenging: existing approaches for robot benchmarking typically rely on heavy standar…

stat.ML2021

Stronger Data Poisoning Attacks Break Data Sanitization Defenses

Pang Wei Koh, Jacob Steinhardt, Percy Liang

Machine learning models trained on data from the outside world can be corrupted by data poisoning attacks that inject malicious points into the models' training sets. A common defe…

cs.LG2020

Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization

Shiori Sagawa, Pang Wei Koh, Tatsunori B. Hashimoto +1

Overparameterized neural networks can be highly accurate on average on an i.i.d. test set yet consistently fail on atypical groups of the data (e.g., by learning spurious correlati…

cs.SD2024

Anticipatory Music Transformer

John Thickstun, David Hall, Chris Donahue +1

We introduce anticipation: a method for constructing a controllable generative model of a temporal point process (the event process) conditioned asynchronously on realizations of a…

cs.CL2018

Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer

Juncen Li, Robin Jia, He He +1

We consider the task of text attribute transfer: transforming a sentence to alter a specific attribute (e.g., sentiment) while preserving its attribute-independent content (e.g., c…

cs.LG2023

Ecosystem Graphs: The Social Footprint of Foundation Models

Rishi Bommasani, Dilara Soylu, Thomas I. Liao +2

Foundation models (e.g. ChatGPT, StableDiffusion) pervasively influence society, warranting immediate social attention. While the models themselves garner much attention, to accura…

cs.LG2020

Concept Bottleneck Models

Pang Wei Koh, Thao Nguyen, Yew Siang Tang +4

We seek to learn models that we can interact with using high-level concepts: if the model did not think there was a bone spur in the x-ray, would it still predict severe arthritis?…

cs.LG2024

AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback

Yann Dubois, Xuechen Li, Rohan Taori +6

Large language models (LLMs) such as ChatGPT have seen widespread adoption due to their strong instruction-following abilities. Developing these LLMs involves a complex yet poorly…

cs.LG2026

Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedback

Hiroki Furuta, Heiga Zen, Dale Schuurmans +4

Large text-to-video models hold immense potential for a wide range of downstream applications. However, they struggle to accurately depict dynamic object interactions, often result…

cs.LG2025

Reinforcement Learning for Machine Learning Engineering Agents

Sherry Yang, Joy He-Yueya, Percy Liang

Existing agents for solving tasks such as ML engineering rely on prompting powerful language models. As a result, these agents do not improve with more experience. In this paper, w…

cs.LG2025

MLE-Smith: Scaling MLE Tasks with Automated Multi-Agent Pipeline

Rushi Qiang, Yuchen Zhuang, Anikait Singh +4

While Language Models (LMs) have made significant progress in automating machine learning engineering (MLE), the acquisition of high-quality MLE training data is significantly cons…

cs.CL2016

Learning Language Games through Interaction

Sida I. Wang, Percy Liang, Christopher D. Manning

We introduce a new language learning setting relevant to building adaptive natural language interfaces. It is inspired by Wittgenstein's language games: a human wishes to accomplis…

cs.LG2023

One-sided Matrix Completion from Two Observations Per Row

Steven Cao, Percy Liang, Gregory Valiant

Given only a few observed entries from a low-rank matrix , matrix completion is the problem of imputing the missing entries, and it formalizes a wide range of real-world setting…

cs.HC2022

CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities

Mina Lee, Percy Liang, Qian Yang

Large language models (LMs) offer unprecedented language generation capabilities and exciting opportunities for interaction design. However, their highly context-dependent capabili…

cs.AI2025

The 2025 Foundation Model Transparency Index

Alexander Wan, Kevin Klyman, Sayash Kapoor +5

Foundation model developers are among the world's most important companies. As these companies become increasingly consequential, how do their transparency practices evolve? The 20…

cs.LG2024

Robust Distortion-free Watermarks for Language Models

Rohith Kuditipudi, John Thickstun, Tatsunori Hashimoto +1

We propose a methodology for planting watermarks in text from an autoregressive language model that are robust to perturbations without changing the distribution over text up to a…

cs.LG2021

Break-It-Fix-It: Unsupervised Learning for Program Repair

Michihiro Yasunaga, Percy Liang

We consider repair tasks: given a critic (e.g., compiler) that assesses the quality of an input, the goal is to train a fixer that converts a bad example (e.g., code with syntax er…

cs.LG2025

The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources

Shayne Longpre, Stella Biderman, Alon Albalak +20

Foundation model development attracts a rapidly expanding body of contributors, scientists, and applications. To help shape responsible development practices, we introduce the Foun…

cs.LG2024

On the Learnability of Watermarks for Language Models

Chenchen Gu, Xiang Lisa Li, Percy Liang +1

Watermarking of language model outputs enables statistical detection of model-generated text, which can mitigate harms and misuses of language models. Existing watermarking strateg…

cs.CL2021

Conditional probing: measuring usable information beyond a baseline

John Hewitt, Kawin Ethayarajh, Percy Liang +1

Probing experiments investigate the extent to which neural representations make properties -- like part-of-speech -- predictable. One suggests that a representation encodes a prope…

cs.CL2018

The price of debiasing automatic metrics in natural language evaluation

Arun Tejasvi Chaganty, Stephen Mussman, Percy Liang

For evaluating generation systems, automatic metrics such as BLEU cost nothing to run but have been shown to correlate poorly with human judgment, leading to systematic bias agains…

cs.LG2023

FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU

Ying Sheng, Lianmin Zheng, Binhang Yuan +11

The high computational and memory requirements of large language model (LLM) inference make it feasible only with multiple high-end accelerators. Motivated by the emerging demand f…

cs.CL2020

The EOS Decision and Length Extrapolation

Benjamin Newman, John Hewitt, Percy Liang +1

Extrapolation to unseen sequence lengths is a challenge for neural generative models of language. In this work, we characterize the effect on length extrapolation of a modeling dec…

cs.LG2018

A Hitting Time Analysis of Stochastic Gradient Langevin Dynamics

Yuchen Zhang, Percy Liang, Moses Charikar

We study the Stochastic Gradient Langevin Dynamics (SGLD) algorithm for non-convex optimization. The algorithm performs stochastic gradient descent, where in each step it injects a…

cs.LG2023

Cheaply Evaluating Inference Efficiency Metrics for Autoregressive Transformer APIs

Deepak Narayanan, Keshav Santhanam, Peter Henderson +3

Large language models (LLMs) power many state-of-the-art systems in natural language processing. However, these models are extremely computationally expensive, even at inference ti…

cs.LG2021

Just Train Twice: Improving Group Robustness without Training Group Information

Evan Zheran Liu, Behzad Haghgoo, Annie S. Chen +5

Standard training via empirical risk minimization (ERM) can produce models that achieve high accuracy on average but low accuracy on certain groups, especially in the presence of s…

cs.LG2015

Reified Context Models

Jacob Steinhardt, Percy Liang

A classic tension exists between exact inference in a simple model and approximate inference in a complex model. The latter offers expressivity and thus accuracy, but the former pr…

cs.CY2025

International Scientific Report on the Safety of Advanced AI (Interim Report)

Yoshua Bengio, Sören Mindermann, Daniel Privitera +41

This is the interim publication of the first International Scientific Report on the Safety of Advanced AI. The report synthesises the scientific understanding of general-purpose AI…

cs.RO2025

WorldGym: World Model as An Environment for Policy Evaluation

Julian Quevedo, Ansh Kumar Sharma, Yixiang Sun +3

Evaluating robot control policies is difficult: real-world testing is costly, and handcrafted simulators require manual effort to improve in realism and generality. We propose a wo…

cs.LG2025

Fantastic Pretraining Optimizers and Where to Find Them

Kaiyue Wen, David Hall, Tengyu Ma +1

AdamW has long been the dominant optimizer in language model pretraining, despite numerous claims that alternative optimizers offer 1.4 to 2x speedup. We posit that two methodologi…

cs.CL2022

Deep Bidirectional Language-Knowledge Graph Pretraining

Michihiro Yasunaga, Antoine Bosselut, Hongyu Ren +4

Pretraining a language model (LM) on text has been shown to help various downstream NLP tasks. Recent works show that a knowledge graph (KG) can complement text data, offering stru…

cs.LG2025

Model Equality Testing: Which Model Is This API Serving?

Irena Gao, Percy Liang, Carlos Guestrin

Users often interact with large language models through black-box inference APIs, both for closed- and open-weight models (e.g., Llama models are popularly accessed via Amazon Bedr…

cs.HC2023

Generative Agents: Interactive Simulacra of Human Behavior

Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai +3

Believable proxies of human behavior can empower interactive applications ranging from immersive environments to rehearsal spaces for interpersonal communication to prototyping too…

cs.LG2023

Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization

Sang Michael Xie, Tengyu Ma, Percy Liang

We focus on prediction problems with structured outputs that are subject to output validity constraints, e.g. pseudocode-to-code translation where the code must compile. While labe…

cs.CL2017

Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings

He He, Anusha Balakrishnan, Mihail Eric +1

We study a symmetric collaborative dialogue setting in which two agents, each with private knowledge, must strategically communicate to achieve a common goal. The open-ended dialog…

cs.LG2019

SPoC: Search-based Pseudocode to Code

Sumith Kulal, Panupong Pasupat, Kartik Chandra +4

We consider the task of mapping pseudocode to long programs that are functionally correct. Given test cases as a mechanism to validate programs, we search over the space of possibl…

cs.LG2024

Ecosystem-level Analysis of Deployed Machine Learning Reveals Homogeneous Outcomes

Connor Toups, Rishi Bommasani, Kathleen A. Creel +3

Machine learning is traditionally studied at the model level: researchers measure and improve the accuracy, robustness, bias, efficiency, and other dimensions of specific models. I…

cs.LG2025

MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering

Rushi Qiang, Yuchen Zhuang, Yinghao Li +8

We introduce MLE-Dojo, a Gym-style framework for systematically reinforcement learning, evaluating, and improving autonomous large language model (LLM) agents in iterative machine…

cs.CY2024

AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies

Yi Zeng, Kevin Klyman, Andy Zhou +6

We present a comprehensive AI risk taxonomy derived from eight government policies from the European Union, United States, and China and 16 company policies worldwide, making a sig…

cs.RO2026

VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model

Yanjiang Guo, Tony Lee, Lucy Xiaoyang Shi +3

The goal of this paper is to improve the performance and reliability of vision-language-action (VLA) models through iterative online interaction. Since collecting policy rollouts i…

cs.CY2024

AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies

Yi Zeng, Yu Yang, Andy Zhou +9

Foundation models (FMs) provide societal benefits but also amplify risks. Governments, companies, and researchers have proposed regulatory frameworks, acceptable use policies, and…

cs.AI2025

Establishing Best Practices for Building Rigorous Agentic Benchmarks

Yuxuan Zhu, Tengjun Jin, Yada Pruksachatkun +22

Benchmarks are essential for quantitatively tracking progress in AI. As AI agents become increasingly capable, researchers and practitioners have introduced agentic benchmarks to e…

cs.AI2025

AHELM: A Holistic Evaluation of Audio-Language Models

Tony Lee, Haoqin Tu, Chi Heem Wong +6

Evaluations of audio-language models (ALMs) -- multimodal models that take interleaved audio and text as input and output text -- are hindered by the lack of standardized benchmark…

cs.CL2021

LM-Critic: Language Models for Unsupervised Grammatical Error Correction

Michihiro Yasunaga, Jure Leskovec, Percy Liang

Training a model for grammatical error correction (GEC) requires a set of labeled ungrammatical / grammatical sentence pairs, but manually annotating such pairs can be expensive. R…

cs.CL2026

Self-Verified Distillation: Your Language Model Is Secretly Its Own Synthetic Data Pipeline

Tony Lee, Percy Liang

Can post-trained large language models (LLMs) further improve themselves using only unlabeled prompts, without external teachers or feedback from tools? We study this setting start…

cs.LG2022

Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?

Rishi Bommasani, Kathleen A. Creel, Ananya Kumar +2

As the scope of machine learning broadens, we observe a recurring theme of algorithmic monoculture: the same systems, or systems that share components (e.g. training data), are dep…

stat.ML2016

Estimating Mixture Models via Mixtures of Polynomials

Sida I. Wang, Arun Tejasvi Chaganty, Percy Liang

Mixture modeling is a general technique for making any simple model more expressive through weighted combination. This generality and simplicity in part explains the success of the…

cs.CL2026

Extracting books from production language models

Ahmed Ahmed, A. Feder Cooper, Sanmi Koyejo +1

Many unresolved legal questions over LLMs and copyright center on memorization: whether specific training data have been encoded in the model's weights during training, and whether…

cs.LG2023

Surgical Fine-Tuning Improves Adaptation to Distribution Shifts

Yoonho Lee, Annie S. Chen, Fahim Tajwar +4

A common approach to transfer learning under distribution shift is to fine-tune the last few layers of a pre-trained model, preserving learned features while also adapting to the n…

cs.LG2020

Understanding and Mitigating the Tradeoff Between Robustness and Accuracy

Aditi Raghunathan, Sang Michael Xie, Fanny Yang +2

Adversarial training augments the training set with perturbations to improve the robust error (over worst-case perturbations), but it often leads to an increase in the standard err…

cs.AI2026

LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals

Joon Sung Park, Carolyn Q. Zou, Jonne Kamphorst +8

Machine learning can predict human behavior well when substantial structured data are available for well-defined outcomes. Such models are typically outcome-specific, however, requ…

cs.CL2025

MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks

Suhana Bedi, Hejie Cui, Miguel Fuentes +78

While large language models (LLMs) achieve near-perfect scores on medical licensing exams, these evaluations inadequately reflect the complexity and diversity of real-world clinica…

cs.CL2022

Trustworthy Social Bias Measurement

Rishi Bommasani, Percy Liang

How do we design measures of social bias that we trust? While prior work has introduced several measures, no measure has gained widespread trust: instead, mounting evidence argues…

cs.CL2020

Selective Question Answering under Domain Shift

Amita Kamath, Robin Jia, Percy Liang

To avoid giving wrong answers, question answering (QA) models need to know when to abstain from answering. Moreover, users often ask questions that diverge from the model's trainin…

cs.LG2022

Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift

Ananya Kumar, Tengyu Ma, Percy Liang +1

We often see undesirable tradeoffs in robust machine learning where out-of-distribution (OOD) accuracy is at odds with in-distribution (ID) accuracy: a robust classifier obtained v…

cs.CL2024

Instruction Following without Instruction Tuning

John Hewitt, Nelson F. Liu, Percy Liang +1

Instruction tuning commonly means finetuning a language model on instruction-response pairs. We discover two forms of adaptation (tuning) that are deficient compared to instruction…

cs.LG2024

Foundation Model Transparency Reports

Rishi Bommasani, Kevin Klyman, Shayne Longpre +5

Foundation models are critical digital technologies with sweeping societal impact that necessitates transparency. To codify how foundation model developers should provide transpare…

cs.CL2021

Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases

Yu Gu, Sue Kase, Michelle Vanni +4

Existing studies on question answering on knowledge bases (KBQA) mainly operate with the standard i.i.d assumption, i.e., training distribution over questions is the same as the te…

cs.LG2025

Blackbox Model Provenance via Palimpsestic Membership Inference

Rohith Kuditipudi, Jing Huang, Sally Zhu +3

Suppose Alice trains an open-weight language model and Bob uses a blackbox derivative of Alice's model to produce text. Can Alice prove that Bob is using her model, either by query…

cs.CL2023

MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records

Scott L. Fleming, Alejandro Lozano, William J. Haberkorn +27

The ability of large language models (LLMs) to follow natural language instructions with human-level fluency suggests many opportunities in healthcare to reduce administrative burd…

cs.CL2023

Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation

Vaishnavi Shrivastava, Percy Liang, Ananya Kumar

To maintain user trust, large language models (LLMs) should signal low confidence on examples where they are incorrect, instead of misleading the user. The standard approach of est…

cs.CL2021

Prefix-Tuning: Optimizing Continuous Prompts for Generation

Xiang Lisa Li, Percy Liang

Fine-tuning is the de facto way to leverage large pretrained language models to perform downstream tasks. However, it modifies all the language model parameters and therefore neces…

cs.LG2023

PRODIGY: Enabling In-context Learning Over Graphs

Qian Huang, Hongyu Ren, Peng Chen +4

In-context learning is the ability of a pretrained model to adapt to novel and diverse downstream tasks by conditioning on prompt examples, without optimizing any parameters. While…

cs.CL2022

Diffusion-LM Improves Controllable Text Generation

Xiang Lisa Li, John Thickstun, Ishaan Gulrajani +2

Controlling the behavior of language models (LMs) without re-training is a major open problem in natural language generation. While recent works have demonstrated successes on cont…

cs.CL2019

Learning Autocomplete Systems as a Communication Game

Mina Lee, Tatsunori B. Hashimoto, Percy Liang

We study textual autocomplete---the task of predicting a full sentence from a partial sentence---as a human-machine communication game. Specifically, we consider three competing go…

cs.CL2023

Backpack Language Models

John Hewitt, John Thickstun, Christopher D. Manning +1

We present Backpacks: a new neural architecture that marries strong modeling performance with an interface for interpretability and control. Backpacks learn multiple non-contextual…

cs.CL2016

Learning Executable Semantic Parsers for Natural Language Understanding

Percy Liang

For building question answering systems and natural language interfaces, semantic parsing has emerged as an important and powerful paradigm. Semantic parsers map natural language i…

cs.LG2022

Large Language Models Can Be Strong Differentially Private Learners

Xuechen Li, Florian Tramèr, Percy Liang +1

Differentially Private (DP) learning has seen limited success for building large deep learning models of text, and straightforward attempts at applying Differentially Private Stoch…

cs.RO2026

RoboReward: General-Purpose Vision-Language Reward Models for Robotics

Tony Lee, Andrew Wagenmaker, Karl Pertsch +3

A well-designed reward is critical for effective reinforcement learning-based policy improvement. In real-world robotics, obtaining such rewards typically requires either labor-int…

cs.CY2025

International AI Safety Report

Yoshua Bengio, Sören Mindermann, Daniel Privitera +93

The first International AI Safety Report comprehensively synthesizes the current evidence on the capabilities, risks, and safety of advanced AI systems. The report was mandated by…

cs.CL2024

Evaluating Human-Language Model Interaction

Mina Lee, Megha Srivastava, Amelia Hardy +15

Many real-world applications of language models (LMs), such as writing assistance and code autocomplete, involve human-LM interaction. However, most benchmarks are non-interactive…

cs.CV2024

VHELM: A Holistic Evaluation of Vision Language Models

Tony Lee, Haoqin Tu, Chi Heem Wong +8

Current benchmarks for assessing vision-language models (VLMs) often focus on their perception or problem-solving capabilities and neglect other critical aspects such as fairness,…

cs.LG2020

Robustness to Spurious Correlations via Human Annotations

Megha Srivastava, Tatsunori Hashimoto, Percy Liang

The reliability of machine learning systems critically assumes that the associations between features and labels remain similar between training and test distributions. However, un…

cs.LG2018

Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on Zero-One Loss

Stephen Mussmann, Percy Liang

Uncertainty sampling, a popular active learning algorithm, is used to reduce the amount of data required to learn a classifier, but it has been observed in practice to converge to…

cs.LG2020

Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately

Fereshte Khani, Percy Liang

The presence of spurious features interferes with the goal of obtaining robust models that perform well across many groups within the population. A natural remedy is to remove spur…

stat.ML2020

Understanding Black-box Predictions via Influence Functions

Pang Wei Koh, Percy Liang

How can we explain the predictions of a black-box model? In this paper, we use influence functions -- a classic technique from robust statistics -- to trace a model's prediction th…

cs.LG2021

In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness

Sang Michael Xie, Ananya Kumar, Robbie Jones +3

Consider a prediction setting with few in-distribution labeled examples and many unlabeled examples both in- and out-of-distribution (OOD). The goal is to learn a model which perfo…

cs.CL2018

Mapping Natural Language Commands to Web Elements

Panupong Pasupat, Tian-Shun Jiang, Evan Zheran Liu +2

The web provides a rich, open-domain environment with textual, structural, and spatial properties. We propose a new task for grounding language in this environment: given a natural…

cs.LG2025

Beat the long tail: Distribution-Aware Speculative Decoding for RL Training

Zelei Shao, Vikranth Srivatsa, Sanjana Srivastava +12

Reinforcement learning(RL) post-training has become essential for aligning large language models (LLMs), yet its efficiency is increasingly constrained by the rollout phase, where…

cs.CL2019

Certified Robustness to Adversarial Word Substitutions

Robin Jia, Aditi Raghunathan, Kerem Göksel +1

State-of-the-art NLP models can often be fooled by adversaries that apply seemingly innocuous label-preserving transformations (e.g., paraphrasing) to input text. The number of pos…

cs.LG2024

MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation

Qian Huang, Jian Vora, Percy Liang +1

A central aspect of machine learning research is experimentation, the process of designing and running experiments, analyzing the results, and iterating towards some positive outco…

cs.CV2022

Is a Caption Worth a Thousand Images? A Controlled Study for Representation Learning

Shibani Santurkar, Yann Dubois, Rohan Taori +2

The development of CLIP [Radford et al., 2021] has sparked a debate on whether language supervision can result in vision models with more transferable representations than traditio…

cs.LG2026

Data-efficient pre-training by scaling synthetic megadocs

Konwoo Kim, Suhas Kotha, Yejin Choi +3

Synthetic data augmentation has emerged as a promising solution when pre-training is constrained by data rather than compute. We study how to design synthetic data algorithms that…

cs.CL2026

Extracting memorized pieces of (copyrighted) books from open-weight language models

A. Feder Cooper, Mark A. Lemley, Allison Casasola +6

Plaintiffs and defendants in copyright lawsuits over generative AI often make sweeping, opposing claims about the extent to which large language models (LLMs) memorize protected ex…

cs.CL2023

Do Question Answering Modeling Improvements Hold Across Benchmarks?

Nelson F. Liu, Tony Lee, Robin Jia +1

Do question answering (QA) modeling improvements (e.g., choice of architecture and training procedure) hold consistently across the diverse landscape of QA benchmarks? To study thi…

cs.CL2021

Swords: A Benchmark for Lexical Substitution with Improved Data Coverage and Quality

Mina Lee, Chris Donahue, Robin Jia +2

We release a new benchmark for lexical substitution, the task of finding appropriate substitutes for a target word in a context. To assist humans with writing, lexical substitution…

math.NA2015

Simultaneous diagonalization: the asymmetric, low-rank, and noisy settings

Volodymyr Kuleshov, Arun Tesjavi Chaganty, Percy Liang

Simultaneous matrix diagonalization is used as a subroutine in many machine learning problems, including blind source separation and paramater estimation in latent variable models.…

cs.CL2024

Introducing v0.5 of the AI Safety Benchmark from MLCommons

Bertie Vidgen, Adarsh Agrawal, Ahmed M. Ahmed +97

This paper introduces v0.5 of the AI Safety Benchmark, which has been created by the MLCommons AI Safety Working Group. The AI Safety Benchmark has been designed to assess the safe…

cs.CL2016

SQuAD: 100,000+ Questions for Machine Comprehension of Text

Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev +1

We present the Stanford Question Answering Dataset (SQuAD), a new reading comprehension dataset consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia article…

cs.CL2020

Robust Encodings: A Framework for Combating Adversarial Typos

Erik Jones, Robin Jia, Aditi Raghunathan +1

Despite excellent performance on many tasks, NLP systems are easily fooled by small adversarial perturbations of inputs. Existing procedures to defend against such perturbations ar…

cs.LG2025

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

A. Feder Cooper, Christopher A. Choquette-Choo, Miranda Bogen +34

"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, copyri…

cs.CL2025

Auditing Prompt Caching in Language Model APIs

Chenchen Gu, Xiang Lisa Li, Rohith Kuditipudi +2

Prompt caching in large language models (LLMs) results in data-dependent timing variations: cached prompts are processed faster than non-cached prompts. These timing differences in…