1k citations · 2.6k across the 149 of their papers we have counts for
79 papers · 1 filter
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…
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…
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…
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…
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…
Understanding Adversarial Transfer: Why Representation-Space Attacks Fail Where Data-Space Attacks Succeed
Isha Gupta, Rylan Schaeffer, Joshua Kazdan +2
The field of adversarial robustness has long established that adversarial examples can successfully transfer between image classifiers and that text jailbreaks can successfully tra…
Evaluating the Robustness of Chinchilla Compute-Optimal Scaling
Rylan Schaeffer, Noam Levi, Andreas Kirsch +4
Hoffman et al (2022)'s Chinchilla paper introduced the principle of compute-optimal scaling, laying a foundation for future scaling of language models. In the years since, however,…
Pretraining Scaling Laws for Generative Evaluations of Language Models
Rylan Schaeffer, Noam Levi, Brando Miranda +1
Neural scaling laws have driven the field's ever-expanding exponential growth in parameters, data and compute. While scaling behaviors for pretraining losses and discriminative ben…
Let's Measure Information Step-by-Step: AI-Based Evaluation Beyond Vibes
Zachary Robertson, Sanmi Koyejo
We evaluate artificial intelligence (AI) systems without ground truth by exploiting a link between strategic gaming and information loss. Building on established information theory…
Position: Machine Learning Conferences Should Establish a "Refutations and Critiques" Track
Rylan Schaeffer, Joshua Kazdan, Yegor Denisov-Blanch +11
Science progresses by iteratively advancing and correcting humanity's understanding of the world. In machine learning (ML) research, rapid advancements have led to an explosion of…
Certified Unlearning for Neural Networks
Anastasia Koloskova, Youssef Allouah, Animesh Jha +2
We address the problem of machine unlearning, where the goal is to remove the influence of specific training data from a model upon request, motivated by privacy concerns and regul…
From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?
Zhanke Zhou, Xiao Feng, Zhaocheng Zhu +3
While existing benchmarks probe the reasoning abilities of large language models (LLMs) across diverse domains, they predominantly assess passive reasoning, providing models with a…
Are Domain Generalization Benchmarks with Accuracy on the Line Misspecified?
Olawale Salaudeen, Nicole Chiou, Shiny Weng +1
Spurious correlations, unstable statistical shortcuts a model can exploit, are expected to degrade performance out-of-distribution (OOD). However, across many popular OOD generaliz…
Decision from Suboptimal Classifiers: Excess Risk Pre- and Post-Calibration
Alexandre Perez-Lebel, Gael Varoquaux, Sanmi Koyejo +2
Probabilistic classifiers are central for making informed decisions under uncertainty. Based on the maximum expected utility principle, optimal decision rules can be derived using…
Preferential Multi-Objective Bayesian Optimization for Drug Discovery
Tai Dang, Long-Hung Pham, Sang T. Truong +6
Despite decades of advancements in automated ligand screening, large-scale drug discovery remains resource-intensive and requires post-processing hit selection, a step where chemis…
Position: Model Collapse Does Not Mean What You Think
Rylan Schaeffer, Joshua Kazdan, Alvan Caleb Arulandu +1
The proliferation of AI-generated content online has fueled concerns over \emph{model collapse}, a degradation in future generative models' performance when trained on synthetic da…
Aligning Compound AI Systems via System-level DPO
Xiangwen Wang, Yibo Jacky Zhang, Zhoujie Ding +3
Compound AI systems, comprising multiple interacting components such as LLMs, foundation models, and external tools, have demonstrated remarkable improvements compared to single mo…