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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Buwei, Liu, Yang, Zhang, Zhaowei, Jia, Zixia, Wu, Huijia, He, Zhaofeng, Zheng, Zilong, Kang, Yipeng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917018079330304
author He, Buwei
Liu, Yang
Zhang, Zhaowei
Jia, Zixia
Wu, Huijia
He, Zhaofeng
Zheng, Zilong
Kang, Yipeng
author_facet He, Buwei
Liu, Yang
Zhang, Zhaowei
Jia, Zixia
Wu, Huijia
He, Zhaofeng
Zheng, Zilong
Kang, Yipeng
contents Persuasion, a fundamental social capability for humans, remains a challenge for AI systems such as large language models (LLMs). Current studies often overlook the strategic use of information asymmetry in message design or rely on strong assumptions regarding pre-commitment. In this work, we explore the application of Bayesian Persuasion (BP) in natural language within single-turn dialogue settings, to enhance the strategic persuasion capabilities of LLMs. Our framework incorporates a commitment-communication mechanism, where the persuader explicitly outlines an information schema by narrating their potential types (e.g., honest or dishonest), thereby guiding the persuadee in performing the intended Bayesian belief update. We evaluate two variants of our approach: Semi-Formal-Natural-Language (SFNL) BP and Fully-Natural-Language (FNL) BP, benchmarking them against both naive and strong non-BP (NBP) baselines within a comprehensive evaluation framework. This framework covers a diverse set of persuadees -- including LLM instances with varying prompts and fine-tuning and human participants -- across tasks ranging from specially designed persuasion scenarios to general everyday situations. Experimental results on LLM-based agents reveal three main findings: (1) LLMs guided by BP strategies consistently achieve higher persuasion success rates than NBP baselines; (2) SFNL exhibits greater credibility and logical coherence, while FNL shows stronger emotional resonance and robustness in naturalistic conversations; (3) with supervised fine-tuning, smaller models can attain BP performance comparable to that of larger models.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13387
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Make an Offer They Can't Refuse: Grounding Bayesian Persuasion in Real-World Dialogues without Pre-Commitment
He, Buwei
Liu, Yang
Zhang, Zhaowei
Jia, Zixia
Wu, Huijia
He, Zhaofeng
Zheng, Zilong
Kang, Yipeng
Computation and Language
Computer Science and Game Theory
Persuasion, a fundamental social capability for humans, remains a challenge for AI systems such as large language models (LLMs). Current studies often overlook the strategic use of information asymmetry in message design or rely on strong assumptions regarding pre-commitment. In this work, we explore the application of Bayesian Persuasion (BP) in natural language within single-turn dialogue settings, to enhance the strategic persuasion capabilities of LLMs. Our framework incorporates a commitment-communication mechanism, where the persuader explicitly outlines an information schema by narrating their potential types (e.g., honest or dishonest), thereby guiding the persuadee in performing the intended Bayesian belief update. We evaluate two variants of our approach: Semi-Formal-Natural-Language (SFNL) BP and Fully-Natural-Language (FNL) BP, benchmarking them against both naive and strong non-BP (NBP) baselines within a comprehensive evaluation framework. This framework covers a diverse set of persuadees -- including LLM instances with varying prompts and fine-tuning and human participants -- across tasks ranging from specially designed persuasion scenarios to general everyday situations. Experimental results on LLM-based agents reveal three main findings: (1) LLMs guided by BP strategies consistently achieve higher persuasion success rates than NBP baselines; (2) SFNL exhibits greater credibility and logical coherence, while FNL shows stronger emotional resonance and robustness in naturalistic conversations; (3) with supervised fine-tuning, smaller models can attain BP performance comparable to that of larger models.
title Make an Offer They Can't Refuse: Grounding Bayesian Persuasion in Real-World Dialogues without Pre-Commitment
topic Computation and Language
Computer Science and Game Theory
url https://arxiv.org/abs/2510.13387