Explaining Large Language Models Decisions Using Shapley Values(arxiv.org)77 points by veryluckyxyz 1 year ago | 18 comments
Adversarial policies beat superhuman Go AIs (2023)(arxiv.org)299 points by amichail 1 year ago | 129 comments
Measuring and Understanding LLM Identity Confusion(arxiv.org)17 points by _____k 1 year ago | 1 comments
Offline Reinforcement Learning for LLM Multi-Step Reasoning(arxiv.org)86 points by belter 1 year ago | 7 comments