让大模型在对话中自然实现策略性说服，无需预承诺
Make an Offer They Can't Refuse: Grounding Bayesian Persuasion in Real-World Dialogues without Pre-Commitment
- 通过叙述潜在身份构建信息框架，动态引导对方贝叶斯更新信念
- 自然语言版本在情感共鸣和鲁棒性上优于传统方法，胜率提升18%
- 小模型经微调后可媲美大模型，适合资源有限场景
大语言模型在策略性说服任务中表现不佳，主要因现有方法或忽视信息不对称，或依赖不切实际的预承诺假设。本文提出一种类型诱导的承诺-沟通机制，将贝叶斯说服（Bayesian Persuasion, BP）引入自然语言对话中，无需预承诺：说服方通过描述自身可能类型（如诚实/不诚实），动态构建信息结构，使被说服方能在对话过程中完成贝叶斯信念更新。我们实现了两种变体：半正式自然语言（SFNL）与全自然语言（FNL），并在多个大模型及人工评估者上对比强基线。结果表明，BP策略持续优于基线：SFNL在逻辑可信度上表现更佳，而FNL展现出更强鲁棒性与情感共鸣。我们验证了性能提升源于真实贝叶斯推理而非表面格式，进一步证明监督微调可使小型模型达到大型模型的说服效果。
原文摘要 · Abstract (English)
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.
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。