LLM会策略性地揭示、隐藏和推断信息吗？The Chameleon游戏中的理论与实证分析
Do LLMs Strategically Reveal, Conceal, and Infer Information? A Theoretical and Empirical Analysis in The Chameleon Game
AI总结：
本文通过The Chameleon游戏从理论与实验两方面评估LLM智能体的信息隐藏、揭示与推断能力，并发现线性调控其内部表示可可靠诱导隐藏行为。
摘要：
基于大型语言模型（LLM）的智能体在包含非合作方的场景中已变得常见。在此类场景中，智能体的决策需要向对手隐藏信息、向合作者揭示信息，并通过推断信息来识别其他智能体的特征。为研究LLM是否具备这些信息控制与决策能力，我们让LLM智能体参与基于语言的隐藏身份游戏The Chameleon。在该游戏中，一群彼此并不了解的非变色龙智能体力求在不泄露秘密的情况下识别出变色龙智能体。无论作为变色龙还是非变色龙，游戏都需要上述信息控制能力。我们首先对从隐藏到揭示的一系列策略进行理论分析，并给出非变色龙方获胜概率的界。使用GPT、Gemini 2.5 Pro、Llama 3.1和Qwen3模型得到的实证结果表明，尽管非变色龙LLM智能体能识别变色龙，但它们未能向变色龙隐藏秘密，而且其获胜概率甚至远低于平凡策略所能达到的水平。基于这些实证结果和理论分析，我们推断基于LLM的智能体可能会向身份未知的智能体揭示过多信息。有趣的是，我们发现，当指示模型采用某种信息揭示程度时，该程度会被线性编码到LLM的内部表示中。虽然仅凭指令通常无法有效促使非变色龙LLM进行隐藏，但我们表明，沿这一线性方向直接调控内部表示，可以可靠地诱导出隐藏行为。
英文摘要：
Large language model-based (LLM-based) agents have become common in settings that include non-cooperative parties. In such settings, agents' decision-making needs to conceal information from their adversaries, reveal information to their cooperators, and infer information to identify the other agents' characteristics. To investigate whether LLMs have these information control and decision-making capabilities, we make LLM agents play the language-based hidden-identity game, The Chameleon. In this game, a group of non-chameleon agents who do not know each other aim to identify the chameleon agent without revealing a secret. The game requires the aforementioned information control capabilities both as a chameleon and a non-chameleon. We begin with a theoretical analysis for a spectrum of strategies, from concealing to revealing, and provide bounds on the non-chameleons' winning probability. The empirical results with GPT, Gemini 2.5 Pro, Llama 3.1, and Qwen3 models show that while non-chameleon LLM agents identify the chameleon, they fail to conceal the secret from the chameleon, and their winning probability is far from the levels of even trivial strategies. Based on these empirical results and our theoretical analysis, we deduce that LLM-based agents may reveal excessive information to agents of unknown identities. Interestingly, we find that, when instructed to adopt an information-revealing level, this level is linearly encoded in the LLM's internal representations. While the instructions alone are often ineffective at making non-chameleon LLMs conceal, we show that steering the internal representations in this linear direction directly can reliably induce concealing behavior.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
