activity
20142024
most citedEight Things to Know about Large Language Models

97 citations · 341 across the 15 of their papers we have counts for

collaborators

15 papers

cs.CL2024

Spontaneous Reward Hacking in Iterative Self-Refinement

Jane Pan, He He, Samuel R. Bowman +1

Language models are capable of iteratively improving their outputs based on natural language feedback, thus enabling in-context optimization of user preference. In place of human u…

cs.AI20249 cited

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…

cs.CL20244 cited

Let's Think Dot by Dot: Hidden Computation in Transformer Language Models

Jacob Pfau, William Merrill, Samuel R. Bowman

Chain-of-thought responses from language models improve performance across most benchmarks. However, it remains unclear to what extent these performance gains can be attributed to…

cs.CL202415 cited

LLM Evaluators Recognize and Favor Their Own Generations

Arjun Panickssery, Samuel R. Bowman, Shi Feng

Self-evaluation using large language models (LLMs) has proven valuable not only in benchmarking but also methods like reward modeling, constitutional AI, and self-refinement. But n…

cs.CR202439 cited

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…

cs.AI20238 cited

Debate Helps Supervise Unreliable Experts

Julian Michael, Salsabila Mahdi, David Rein +4

As AI systems are used to answer more difficult questions and potentially help create new knowledge, judging the truthfulness of their outputs becomes more difficult and more impor…