1.5k citations · 3.8k across the 46 of their papers we have counts for
4 papers · 1 filter
Code Monitor Red Teaming for Public-Test-Passing Code
Junchi Liao, Jiawen Deng, Fuji Ren
Visible tests are a common gate for LLM-generated code, but passing them does not certify specification correctness. We study a deployment-like monitoring problem: after code has p…
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…
Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
Carson Denison, Monte MacDiarmid, Fazl Barez +11
In reinforcement learning, specification gaming occurs when AI systems learn undesired behaviors that are highly rewarded due to misspecified training goals. Specification gaming c…
Measuring Faithfulness in Chain-of-Thought Reasoning
Tamera Lanham, Anna Chen, Ansh Radhakrishnan +27
Large language models (LLMs) perform better when they produce step-by-step, "Chain-of-Thought" (CoT) reasoning before answering a question, but it is unclear if the stated reasonin…