130 citations · 238 across the 12 of their papers we have counts for
7 papers · 1 filter
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…
Sabotage Evaluations for Frontier Models
Joe Benton, Misha Wagner, Eric Christiansen +13
Sufficiently capable models could subvert human oversight and decision-making in important contexts. For example, in the context of AI development, models could covertly sabotage e…
Language Models Learn to Mislead Humans via RLHF
Jiaxin Wen, Ruiqi Zhong, Akbir Khan +6
Language models (LMs) can produce errors that are hard to detect for humans, especially when the task is complex. RLHF, the most popular post-training method, may exacerbate this p…
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…
Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought
James Chua, Edward Rees, Hunar Batra +4
Chain-of-thought prompting (CoT) has the potential to improve the explainability of language model reasoning. But CoT can also systematically misrepresent the factors influencing m…
Debating with More Persuasive LLMs Leads to More Truthful Answers
Akbir Khan, John Hughes, Dan Valentine +7
Common methods for aligning large language models (LLMs) with desired behaviour heavily rely on human-labelled data. However, as models grow increasingly sophisticated, they will s…
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
Evan Hubinger, Carson Denison, Jesse Mu +36
Humans are capable of strategically deceptive behavior: behaving helpfully in most situations, but then behaving very differently in order to pursue alternative objectives when giv…