activity
20242026
collaborators

6 papers

cs.CL2026

Stabilizing Efficient Reasoning with Step-Level Advantage Selection

Han Wang, Xiaodong Yu, Jialian Wu +4

Large language models (LLMs) achieve strong reasoning performance by allocating substantial computation at inference time, often generating long and verbose reasoning traces. While…

cs.CL2026

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…

cs.AI2025

Inverse Scaling in Test-Time Compute

Aryo Pradipta Gema, Alexander Hägele, Runjin Chen +11

We construct evaluation tasks where extending the reasoning length of Large Reasoning Models (LRMs) deteriorates performance, exhibiting an inverse scaling relationship between tes…

cs.AI2025

SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents

Jonathan Kutasov, Yuqi Sun, Paul Colognese +9

As Large Language Models (LLMs) are increasingly deployed as autonomous agents in complex and long horizon settings, it is critical to evaluate their ability to sabotage users by p…

cs.CL2025

Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming

Mrinank Sharma, Meg Tong, Jesse Mu +40

Large language models (LLMs) are vulnerable to universal jailbreaks-prompting strategies that systematically bypass model safeguards and enable users to carry out harmful processes…

cs.AI2024

Alignment faking in large language models

Ryan Greenblatt, Carson Denison, Benjamin Wright +17

We present a demonstration of a large language model engaging in alignment faking: selectively complying with its training objective in training to prevent modification of its beha…