290 citations · 1k across the 14 of their papers we have counts for
16 papers
Code Monitor Red Teaming for Public-Test-Passing Code
Junchi Liao, Jiawen Deng, Fuji Ren
Visible tests are a common gate for LLM-generated code, but passing them does not certify specification correctness. We study a deployment-like monitoring problem: after code has p…
CLExEval: A Human-in-the-Loop Framework for Qualitative Evaluation of LLM Clinical Reasoning
Ajmal M., Abin Roy, Afthab Salam Kanniyan +4
Large Language Models (LLMs) achieve strong results on many medical benchmarks, but their clinical reasoning remains difficult to evaluate reliably. A central risk is an evaluation…
TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models
Jinho Choo, JunSeung Lee, Jimyeong Kim +3
Large language models (LLMs) demonstrate strong multilingual capabilities, yet often fail to consistently generate responses in the intended language, exhibiting a phenomenon known…
Chunky Post-Training: Data Driven Failures of Generalization
Seoirse Murray, Allison Qi, Timothy Qian +3
LLM post-training involves many diverse datasets, each targeting a specific behavior. But these datasets encode incidental patterns alongside intended ones: correlations between fo…
CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning
Congmin Zheng, Jiachen Zhu, Jianghao Lin +6
Process Reward Models (PRMs) play a central role in evaluating and guiding multi-step reasoning in large language models (LLMs), especially for mathematical problem solving. Howeve…
Unsupervised Elicitation of Language Models
Jiaxin Wen, Zachary Ankner, Arushi Somani +10
To steer pretrained language models for downstream tasks, today's post-training paradigm relies on humans to specify desired behaviors. However, for models with superhuman capabili…
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner +9
Widely used alignment techniques, such as reinforcement learning from human feedback (RLHF), rely on the ability of humans to supervise model behavior - for example, to evaluate wh…
Discovering Latent Knowledge in Language Models Without Supervision
Collin Burns, Haotian Ye, Dan Klein +1
Existing techniques for training language models can be misaligned with the truth: if we train models with imitation learning, they may reproduce errors that humans make; if we tra…
Measuring Coding Challenge Competence With APPS
Dan Hendrycks, Steven Basart, Saurav Kadavath +8
While programming is one of the most broadly applicable skills in modern society, modern machine learning models still cannot code solutions to basic problems. Despite its importan…
Limitations of Post-Hoc Feature Alignment for Robustness
Collin Burns, Jacob Steinhardt
Feature alignment is an approach to improving robustness to distribution shift that matches the distribution of feature activations between the training distribution and test distr…
CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review
Dan Hendrycks, Collin Burns, Anya Chen +1
Many specialized domains remain untouched by deep learning, as large labeled datasets require expensive expert annotators. We address this bottleneck within the legal domain by int…
Measuring Mathematical Problem Solving With the MATH Dataset
Dan Hendrycks, Collin Burns, Saurav Kadavath +5
Many intellectual endeavors require mathematical problem solving, but this skill remains beyond the capabilities of computers. To measure this ability in machine learning models, w…
Measuring Massive Multitask Language Understanding
Dan Hendrycks, Collin Burns, Steven Basart +4
We propose a new test to measure a text model's multitask accuracy. The test covers 57 tasks including elementary mathematics, US history, computer science, law, and more. To attai…
Aligning AI With Shared Human Values
Dan Hendrycks, Collin Burns, Steven Basart +4
We show how to assess a language model's knowledge of basic concepts of morality. We introduce the ETHICS dataset, a new benchmark that spans concepts in justice, well-being, dutie…
Streaming Complexity of SVMs
Alexandr Andoni, Collin Burns, Yi Li +2
We study the space complexity of solving the bias-regularized SVM problem in the streaming model. This is a classic supervised learning problem that has drawn lots of attention, in…
Interpreting Black Box Models via Hypothesis Testing
Collin Burns, Jesse Thomason, Wesley Tansey
In science and medicine, model interpretations may be reported as discoveries of natural phenomena or used to guide patient treatments. In such high-stakes tasks, false discoveries…