1k citations · 2.6k across the 149 of their papers we have counts for
154 papers
Auditing of Unlearning Algorithms
Sahasrajit Sarmasarkar, Anastasia Koloskova, Sanmi Koyejo
Evaluating whether unlearning algorithms truly remove training data influence remains an open challenge. We propose a practical auditor that computes data-dependent lower bounds on…
AI Writes Faster Than Humans Can Review: A Longitudinal Study of an Enterprise 2x Mandate
Hao He, Shyam Agarwal, Yegor Denisov-Blanch +3
Enterprises increasingly mandate AI coding tools and report large productivity gains, yet longitudinal evidence on how such a mandate unfolds is scarce. In this paper, we present a…
Gaming Consensus: Coordinated Manipulation in Crowdsourced Fact-Checking
Nikil Roashan Selvam, Jay Baxter, Sophie Hilgard +4
Crowdsourced fact-checking systems have been adopted by major social media companies such as X, Meta, TikTok and Google with the aim of combating misleading information at scale wi…
Internal Data Repetition Destroys Language Models
Jessica Chudnovsky, Joshua Kazdan, Noam Levi +6
Language models are running out of high-quality training data, and even aggressively deduplicated corpora retain some amount of repetition. Earlier controlled studies predated Chin…
CARE: A Conformal Safety Layer for Medical Summarization
Suhana Bedi, Bridget Lin, Anson Y. Zhou +5
Large language models (LLMs) are increasingly used for medical summarization, but their outputs can omit medically important information and introduce unsupported claims. Existing…
The Easy, the Hard, and the Learnable: Confidence and Difficulty-Adaptive Policy Optimization for LLM Reasoning
Zhanke Zhou, Xiangyu Lu, Chentao Cao +4
RL with verifiable rewards can substantially improve LLM reasoning, yet standard GRPO-style training often treats easy, hard, and learnable questions alike through uniform sampling…
Reasoning Models Don't Just Think Longer, They Move Differently
Anders Gjølbye, Lars Kai Hansen, Sanmi Koyejo
Reasoning-trained language models often spend more tokens on harder problems, but longer chains of thought do not show whether a model is merely computing for more steps or followi…
When Behavioral Safety Evaluation Fails: A Representation-Level Perspective
Enyi Jiang, Anders Gjølbye, Yibo Jacky Zhang +1
Safety evaluation of large language models (LLMs) is largely behavioral: a model is certified safe when it refuses harmful requests and answers benign ones. But refusing on the pro…
Item Response Scaling Laws: A Measurement Theory Approach for Efficient and Generalizable Neural Scaling Estimation
Sang Truong, Yuheng Tu, Rylan Schaeffer +1
Scaling laws provide a fundamental framework for understanding the performance of Language Models (LMs), yet deriving them requires prohibitively expensive evaluations across thous…
Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation
Andreas Haupt, Justin Hartenstein, Anka Reuel +2
AI benchmarks have well-documented limitations, with prior work examining contamination, saturation, and construct underspecification. Aggregation has received far less attention:…
The Distillation Game: Adaptive Evaluations & Efficient Defenses
Youssef Allouah, Mahdi Haghifam, Sanmi Koyejo +1
Distillation attacks create a deployment trade-off for model providers: the same outputs that make a model more useful can also make it easier to imitate. We study this trade-off t…
General Preference Reinforcement Learning
Muhammad Umer, Muhammad Ahmed Mohsin, Ahsan Bilal +5
Post-training has split large language model (LLM) alignment into two largely disconnected tracks. Online reinforcement learning (RL) with verifiable rewards drives emergent reason…
Why Do Safety Guardrails Degrade Across Languages?
Max Zhang, Ameen Patel, Sang T. Truong +1
Large language models exhibit safety degradation in non-English languages. Standard evaluation relies on Jailbreak Success Rate (JSR), which confounds several safety-driving factor…
HealthAdminBench: Evaluating Computer-Use Agents on Healthcare Administration Tasks
Suhana Bedi, Ryan Welch, Ethan Steinberg +12
Healthcare administration accounts for over $1 trillion in annual spending, making it a promising target for LLM-based computer-use agents (CUAs). While clinical applications of LL…
Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Image Diffusion
Sathwik Karnik, Juyeop Kim, Sanmi Koyejo +2
Text-to-image diffusion models often memorize training data, revealing a fundamental failure to generalize beyond the training set. Current mitigation strategies typically sacrific…
TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots
Fangrui Huang, Souhad Chbeir, Arpandeep Khatua +8
Large language models (LLMs) are increasingly used for mental-health support; yet prevailing evaluation methods--fluency metrics, preference tests, and generic dialogue benchmarks-…
Consensus is Not Verification: Why Crowd Wisdom Strategies Fail for LLM Truthfulness
Yegor Denisov-Blanch, Joshua Kazdan, Jessica Chudnovsky +4
Pass@k and other methods of scaling inference compute can improve language model performance in domains with external verifiers, including mathematics and code, where incorrect can…
ALMo: Interactive Aim-Limit-Defined, Multi-Objective System for Personalized High-Dose-Rate Brachytherapy Treatment Planning and Visualization for Cervical Cancer
Edward Chen, Natalie Dullerud, Pang Wei Koh +4
In complex clinical decision-making, clinicians must often track a variety of competing metrics defined by aim (ideal) and limit (strict) thresholds. Sifting through these high-dim…
Discovering Implicit Large Language Model Alignment Objectives
Edward Chen, Sanmi Koyejo, Carlos Guestrin
Large language model (LLM) alignment relies on complex reward signals that often obscure the specific behaviors being incentivized, creating critical risks of misalignment and rewa…
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…
Fantastic Bugs and Where to Find Them in AI Benchmarks
Sang Truong, Yuheng Tu, Michael Hardy +8
Benchmarks are pivotal in driving AI progress, and invalid benchmark questions frequently undermine their reliability. Manually identifying and correcting errors among thousands of…
CURE: Cultural Understanding and Reasoning Evaluation - A Framework for "Thick" Culture Alignment Evaluation in LLMs
Truong Vo, Sanmi Koyejo
Large language models (LLMs) are increasingly deployed in culturally diverse environments, yet existing evaluations of cultural competence remain limited. Existing methods focus on…
SpecEval: Evaluating Model Adherence to Behavior Specifications
Ahmed Ahmed, Kevin Klyman, Yi Zeng +2
Companies that develop foundation models publish behavioral guidelines they pledge their models will follow, but it remains unclear if models actually do so. While providers such a…
The Sound of Syntax: Finetuning and Comprehensive Evaluation of Language Models for Speech Pathology
Fagun Patel, Duc Q. Nguyen, Sang T. Truong +3
According to the U.S. National Institutes of Health, more than 3.4 million children experience speech disorders that require clinical intervention. The number of speech-language pa…