提出无法拒绝的方案：在无预承诺的真实对话中建立贝叶斯说服
Make an Offer They Can't Refuse: Grounding Bayesian Persuasion in Real-World Dialogues without Pre-Commitment
AI总结：
该研究针对LLM策略性说服的不足，提出无预承诺的贝叶斯说服机制，实现两种变体并经多LLM与人类评估，验证其性能提升源于贝叶斯推理，且微调可缩小模型性能差距。
摘要：
大型语言模型（LLMs）在策略性说服方面仍存在不足，主要是因为现有方法要么忽视信息不对称，要么依赖不切实际的预承诺假设。我们提出一种类型诱导的承诺-通信机制，在无预承诺的自然语言对话中建立贝叶斯说服（BP）：说服者叙述自身潜在类型（如诚实型与不诚实型），动态构建信息模式，使被说服者在对话过程中进行贝叶斯信念更新。我们实现两种变体：半形式自然语言（SFNL）与全自然语言（FNL），在多个LLMs及人类评判者中与强基准模型对比评估。BP策略始终优于基准模型：SFNL在逻辑可信度上表现突出，FNL则展现出更优的鲁棒性与情感共鸣。我们验证性能提升源于真实贝叶斯推理而非表面格式，还进一步表明，监督微调可使小型模型达到远更大模型的说服性能。
英文摘要：
Large language models (LLMs) still struggle with strategic persuasion, largely because existing approaches either neglect information asymmetry or rely on unrealistic pre-commitment assumptions. We introduce a type-induced commitment-communication mechanism that grounds Bayesian Persuasion (BP) in natural language dialogue without pre-commitment: the persuader narrates their potential types (e.g., honest vs. dishonest) to dynamically construct an information schema, enabling the persuadee to perform Bayesian belief updates within the conversation itself. We implement two variants: Semi-Formal-Natural-Language (SFNL) and Fully-Natural-Language (FNL), evaluating them against strong baselines across multiple LLMs and human judges. BP strategies consistently outperform baselines: SFNL excels in logical credibility, while FNL shows superior robustness and emotional resonance. We verify that gains stem from genuine Bayesian reasoning rather than superficial formatting, and we further show that supervised fine-tuning enables small models to match the persuasive performance of much larger ones.
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。
