EMNLP Findings2024
Zero-shot Persuasive Chatbots with LLM-Generated Strategies and Information Retrieval
Kazuaki Furumai, Roberto Legaspi, Julio Romero, Yudai Yamazaki, Yasutaka Nishimura, Sina J. Semnani, Kazushi Ikeda, Weiyan Shi, Monica S. Lam
Abstract
Persuasion plays a pivotal role in a wide range of applications from health intervention to the promotion of social good. Persuasive chatbots employed responsibly for social good can be an enabler of positive individual and social change. Existing methods rely on fine-tuning persuasive chatbots with task-specific training data which is costly, if not infeasible, to collect. Furthermore, they employ only a handful of pre-defined persuasion strategies. We propose PersuaBot, a zero-shot chatbot based on Large Language Models (LLMs) that is factual and more persuasive by leveraging many more nuanced strategies. PersuaBot uses an LLM to first generate natural responses, from which the strategies used are extracted. To combat hallucination of LLMs, Persuabot replace any unsubstantiated claims in the response with retrieved facts supporting the extracted strategies. We applied our chatbot, PersuaBot, to three significantly different domains needing persuasion skills: donation solicitation, recommendations, and health intervention. Our experiments on simulated and human conversations show that our zero-shot approach is more persuasive than prior work, while achieving factual accuracy surpassing state-of-the-art knowledge-oriented chatbots.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers1
Builds on14
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step QuestionsHarsh Trivedi, Niranjan Balasubramanian, Tushar Khot, Ashish SabharwalACL 2023 · 187 citations
- MedDialog: Large-scale Medical Dialogue DatasetsGuangtao Zeng, Wenmian Yang, Zeqian Ju, Yue Yang et al.EMNLP 2020 · 163 citations
- You Impress Me: Dialogue Generation via Mutual Persona PerceptionQian Liu, Yihong Chen, Bei Chen, Jian-Guang Lou et al.ACL 2020 · 144 citations
- Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood TrainingMargaret Li, Stephen Roller, Ilia Kulikov, Sean Welleck et al.ACL 2020 · 120 citations
Related papers
- Vulnerability of LLMs' Stated Belief? LLMs Belief Resistance Check Through Strategic Persuasive Conversation InterventionsFan Huang, Haewoon Kwak, Jisun AnACL Findings 2026
- Persuading across Diverse Domains: a Dataset and Persuasion Large Language ModelChuhao Jin, Kening Ren, Lingzhen Kong, Xiting Wang et al.ACL 2024 · 9 citations
- Towards Strategic Persuasion with Language ModelsZirui Cheng, Jiaxuan YouICLR 2026 · 11 citations
- Working With AI to Persuade: Examining a Large Language Model's Ability to Generate Pro-Vaccination MessagesElise Karinshak, Sunny Xun Liu, Joon Sung Park, Jeffrey T. HancockCSCW 2023 · 163 citations
- The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive ConversationRongwu Xu, Brian S. Lin, Shujian Yang, Tianqi Zhang et al.ACL 2024
