Zero-shot Persuasive Chatbots with LLM-Generated Strategies and Information Retrieval
This addresses the challenge of costly data collection for persuasive chatbots, enabling broader applications for social good, though it is incremental in combining existing techniques.
The paper tackles the problem of building persuasive chatbots without task-specific training data by proposing PersuaBot, a zero-shot approach using LLMs to generate responses and retrieve facts to ensure factual accuracy, achieving higher persuasiveness and factual accuracy than prior methods in domains like donation solicitation, recommendations, and health intervention.
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.