A new paper identifies two key internal gaps that cause large language models to struggle with strategic decision-making in situations with incomplete information. The research found an "observation-belief gap" where LLMs' internal beliefs are more accurate than their verbal reports but are brittle and degrade with complex reasoning. Additionally, a "belief-action gap" was observed, indicating that LLMs' actions are weakly conditioned on their internal beliefs, leading to systematic vulnerabilities. AI
影响 Highlights systematic vulnerabilities in LLMs for strategic tasks, urging caution in deployment without guardrails.
排序理由 Academic paper detailing findings on LLM decision-making limitations.
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
