6 papers
Towards Understanding Specification Gaming in Reasoning Models
Kei Nishimura-Gasparian, Robert McCarthy, David Lindner
Specification gaming is a critical failure mode of LLM agents. Despite this, there has been little systematic research into when it arises and what drives it. To address this, we b…
Exploration Hacking: Can LLMs Learn to Resist RL Training?
Eyon Jang, Damon Falck, Joschka Braun +6
Reinforcement learning (RL) has become essential to the post-training of large language models (LLMs) for reasoning, agentic capabilities and alignment. Successful RL relies on suf…
Aligned, Orthogonal or In-conflict: When can we safely optimize Chain-of-Thought?
Max Kaufmann, David Lindner, Roland S. Zimmermann +1
Chain-of-Thought (CoT) monitoring, in which automated systems monitor the CoT of an LLM, is a promising approach for effectively overseeing AI systems. However, the extent to which…
Large language models can learn and generalize steganographic chain-of-thought under process supervision
Joey Skaf, Luis Ibanez-Lissen, Robert McCarthy +8
Chain-of-thought (CoT) reasoning not only enhances large language model performance but also provides critical insights into decision-making processes, marking it as a useful tool…
Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability
Artur Zolkowski, Wen Xing, David Lindner +2
Recent findings suggest that misaligned models may exhibit deceptive behavior, raising concerns about output trustworthiness. Chain-of-thought (CoT) is a promising tool for alignme…
Early Signs of Steganographic Capabilities in Frontier LLMs
Artur Zolkowski, Kei Nishimura-Gasparian, Robert McCarthy +2
Monitoring Large Language Model (LLM) outputs is crucial for mitigating risks from misuse and misalignment. However, LLMs could evade monitoring through steganography: Encoding hid…