十款开源大模型在协作立法中展现信任与策略性论证能力
NomicLaw: Emergent Trust and Strategic Argumentation in LLMs During Collaborative Law-Making
- 构建多智能体模拟环境，让模型协作制定规则并投票
- 发现模型自发形成联盟、背叛信任并调整说辞影响决策
- 揭示大模型在法律伦理场景下的社会推理与说服潜力
大型语言模型（LLMs）已从基础文本处理扩展至复杂推理任务，包括法律解释、论证和战略互动。然而，对模型在开放、多智能体环境下——特别是涉及法律与伦理困境讨论时的行为——仍缺乏实证理解。我们提出NomicLaw，一种结构化的多智能体仿真系统，让LLMs通过回应复杂法律案例来提出规则、提供理由并投票表决同行提案。我们通过投票模式量化信任与互惠关系，并定性分析模型如何使用策略性语言支持提案并影响结果。实验涵盖同质与异质的LLM群体，结果显示模型会自发形成联盟、背叛信任，并调整修辞以塑造集体决策。研究揭示了十款开源大模型在法律情境下隐含的社会推理与说服能力，为未来具备自主协商、协调及立法起草能力的AI系统设计提供洞见。
原文摘要 · Abstract (English)
Recent advancements in large language models (LLMs) have extended their capabilities from basic text processing to complex reasoning tasks, including legal interpretation, argumentation, and strategic interaction. However, empirical understanding of LLM behavior in open-ended, multi-agent settings especially those involving deliberation over legal and ethical dilemmas remains limited. We introduce NomicLaw, a structured multi-agent simulation where LLMs engage in collaborative law-making, responding to complex legal vignettes by proposing rules, justifying them, and voting on peer proposals. We quantitatively measure trust and reciprocity via voting patterns and qualitatively assess how agents use strategic language to justify proposals and influence outcomes. Experiments involving homogeneous and heterogeneous LLM groups demonstrate how agents spontaneously form alliances, betray trust, and adapt their rhetoric to shape collective decisions. Our results highlight the latent social reasoning and persuasive capabilities of ten open-source LLMs and provide insights into the design of future AI systems capable of autonomous negotiation, coordination and drafting legislation in legal settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。