arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.03585cs.CL
收藏

利用 LLM 生成策略与信息检索的零样本说服型聊天机器人

Zero-shot Persuasive Chatbots with LLM-Generated Strategies and Information Retrieval

KDDI Research, Inc.(KDDI研究所);Stanford University(斯坦福大学)

Kazuaki Furumai, Roberto Legaspi, Julio Vizcarra, Yudai Yamazaki, Yasutaka Nishimura, Sina J. Semnani, Kazushi Ikeda, Weiyan Shi, Monica S. Lam

AI总结:

本文提出零样本说服型聊天机器人 PersuaBot,结合 LLM 策略生成、提取与检索事实验证,在募捐、推荐和健康干预中提升说服力与事实准确性。

摘要:

说服在从健康干预到促进社会公益的广泛应用中发挥着关键作用。负责任地用于社会公益的说服型聊天机器人,能够推动积极的个人与社会变革。现有方法依赖使用特定任务训练数据对说服型聊天机器人进行微调,而这些数据即便并非无法收集,成本也很高昂。此外,它们只采用少数几种预定义的说服策略。我们提出 PersuaBot,这是一种基于大型语言模型(LLM)的零样本聊天机器人,通过利用多得多的细致策略,使其具备事实性且更具说服力。PersuaBot 首先使用 LLM 生成自然回复,并从中提取所使用的策略。为应对 LLM 的幻觉问题,PersuaBot 会用支持所提取策略的检索事实替换回复中任何未经证实的主张。我们将聊天机器人 PersuaBot 应用于三个需要说服技能且显著不同的领域:募捐、推荐和健康干预。在模拟对话和人类对话上的实验表明,我们的零样本方法比以往工作更具说服力,同时实现了超越最先进知识导向型聊天机器人的事实准确性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑