English(EN) Make an Offer They Can't Refuse: Grounding Bayesian Persuasion in Real-World Dialogues without Pre-Commitment

新方法在无预先承诺的LLM对话中实现贝叶斯说服

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-01 04:00

研究人员开发了一种新的方法，可以在自然语言对话中实现贝叶斯说服，而无需参与者预先承诺。该方法有两种变体：半正式自然语言（SFNL）和完全自然语言（FNL）。它允许大型语言模型（LLM）通过叙述潜在类型来动态构建信息模式，使被说服者能够在对话中更新其信念。评估表明，这些贝叶斯说服策略始终优于基线，其中SFNL表现出强大的逻辑可信度，而FNL则提供了卓越的鲁棒性和情感共鸣。研究还证实，收益归因于真正的贝叶斯推理，并且通过监督微调可以使较小的模型达到与较大模型相同的说服性能。 AI

影响这项研究可以通过实现更复杂的说服性对话来增强LLM在谈判和销售中的战略能力。

排序理由该集群包含一篇详细介绍LLM新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 24 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍LLM新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Buwei He, Yang Liu, Zhaowei Zhang, Zixia Jia, Yang Yu, Huijia Wu, Zhaofeng He, Zilong Zheng, Yipeng Kang · 2026-09-01 04:00

开出对方无法拒绝的条件：在无预先承诺的现实对话中实现贝叶斯劝说的基础

arXiv:2510.13387v3 Announce Type: replace Abstract: 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 commi…

本文如何被排名

报道来源 [1]

开出对方无法拒绝的条件：在无预先承诺的现实对话中实现贝叶斯劝说的基础

相关实体

相关话题