Avalon的思想博弈：通过递归沉思对抗欺骗
Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation
AI总结：
本研究以Avalon游戏为测试平台，提出递归沉思框架，通过结合构建与精炼沉思及一阶、二阶视角转换，在不需额外微调的情况下有效提升LLM识别与对抗欺骗信息的能力。
摘要：
大型语言模型（LLMs）的近期突破为LLM作为智能体领域带来了显著成功。然而，一个普遍的假设是LLM处理的信息始终是诚实的，忽视了人类社会和AI生成内容中普遍存在的欺骗性或误导性信息。这一疏忽使得LLM容易受到恶意操纵，可能导致有害后果。本研究以复杂的Avalon游戏为测试平台，探索LLM在欺骗性环境中的潜力。Avalon充斥着错误信息并需要复杂的逻辑，表现为一场“思想博弈”。受人类在Avalon游戏中递归思考和视角转换有效性的启发，我们引入了一个名为递归沉思的全新框架，以增强LLM识别和对抗欺骗性信息的能力。ReCon结合了构建沉思和精炼沉思过程；构建沉思生成初步想法和发言，而精炼沉思则进一步对其进行润色。此外，我们分别将一阶和二阶视角转换融入这些过程。具体而言，一阶允许LLM智能体推断他人的心理状态，而二阶涉及理解他人如何看待该智能体的心理状态。在将ReCon与不同的LLM集成后，来自Avalon游戏的大量实验结果表明其在帮助LLM识别和规避欺骗性信息方面具有有效性，且无需额外的微调和数据。最后，我们为ReCon的有效性提供了可能的解释，并探讨了LLM在安全性、推理、说话风格和格式方面的当前局限性，为后续研究提供了见解。
英文摘要：
Recent breakthroughs in large language models (LLMs) have brought remarkable success in the field of LLM-as-Agent. Nevertheless, a prevalent assumption is that the information processed by LLMs is consistently honest, neglecting the pervasive deceptive or misleading information in human society and AI-generated content. This oversight makes LLMs susceptible to malicious manipulations, potentially resulting in detrimental outcomes. This study utilizes the intricate Avalon game as a testbed to explore LLMs' potential in deceptive environments. Avalon, full of misinformation and requiring sophisticated logic, manifests as a "Game-of-Thoughts". Inspired by the efficacy of humans' recursive thinking and perspective-taking in the Avalon game, we introduce a novel framework, Recursive Contemplation (ReCon), to enhance LLMs' ability to identify and counteract deceptive information. ReCon combines formulation and refinement contemplation processes; formulation contemplation produces initial thoughts and speech, while refinement contemplation further polishes them. Additionally, we incorporate first-order and second-order perspective transitions into these processes respectively. Specifically, the first-order allows an LLM agent to infer others' mental states, and the second-order involves understanding how others perceive the agent's mental state. After integrating ReCon with different LLMs, extensive experiment results from the Avalon game indicate its efficacy in aiding LLMs to discern and maneuver around deceptive information without extra fine-tuning and data. Finally, we offer a possible explanation for the efficacy of ReCon and explore the current limitations of LLMs in terms of safety, reasoning, speaking style, and format, potentially furnishing insights for subsequent research.
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。
