activity
20242026
collaborators
Showing 2025Show all

14 papers · 1 filter

cs.AI2025

Efficient Prediction of Pass@k Scaling in Large Language Models

Joshua Kazdan, Rylan Schaeffer, Youssef Allouah +4

Assessing the capabilities and risks of frontier AI systems is a critical area of research, and recent work has shown that repeated sampling from models can dramatically increase b…

cs.LG2025

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…

cs.LG2025

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,…

cs.CR2025

No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms

Joshua Kazdan, Abhay Puri, Rylan Schaeffer +5

Leading language model (LM) providers like OpenAI and Anthropic allow customers to fine-tune frontier LMs for specific use cases. To prevent abuse, these providers apply filters to…

cs.LG2025

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…

cs.CL2025

Beyond Scale: The Diversity Coefficient as a Data Quality Metric for Variability in Natural Language Data

Brando Miranda, Alycia Lee, Sudharsan Sundar +4

Current trends in pre-training Large Language Models (LLMs) primarily focus on the scaling of model and dataset size. While the quality of pre-training data is considered an import…