Abstract:Persuasive dialogue requires reasoning about others' latent mental states, a capability known as Theory of Mind (ToM). However, due to reliance on simple prompting strategies and insufficient ToM knowledge, existing LLMs often fail to capture the intrinsic dependencies among mental states, leading to fragmented representations and unstable reasoning. To address these challenges, we introduce the ToM-based Persuasive Dialogue (ToM-PD) task, grounded in the Belief-Desire-Intention (BDI) framework, which explicitly models the sequential dependencies among mental states in multi-turn dialogues. To facilitate research on this task, we construct a large-scale annotated dataset, ToM-based Broad Persuasive Dialogues (ToM-BPD), capturing fine-grained mental states and corresponding persuasive strategies. We further propose Think Thrice Before You Speak (TTBYS), a knowledge-enhanced stepwise reasoning framework that leverages both explicit and implicit prior experiences to improve LLMs' inference of desires, beliefs, and persuasive strategies. Experimental results demonstrate that Qwen3-8B equipped with TTBYS outperforms GPT-5 by 1.20%, 22.80%, and 16.97% in predicting desires, beliefs, and persuasive strategies, respectively. Case studies further show that our approach enhances interpretability and consistency in reasoning.
| Comments: | 19 pages, 6 figures |
| Subjects: | Artificial Intelligence (cs.AI) |
| MSC classes: | 68Q32 (Primary), 68T07, 68T05 (Secondary) |
| ACM classes: | I.2.7; I.2.6; H.5.2 |
| Cite as: | arXiv:2605.22602 [cs.AI] |
| (or arXiv:2605.22602v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.22602 arXiv-issued DOI via DataCite (pending registration) |
From: Lucian Ma [view email]
[v1]
Thu, 21 May 2026 15:15:51 UTC (2,200 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。