arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.01644cs.HCcs.AIcs.CL
收藏

面向工具赋能对话智能体的插入扩展

Insert-expansions for Tool-enabled Conversational Agents

University of St.Gallen(圣加仑大学)

Andreas Göldi, Roman Rietsche

AI总结:

本文针对工具赋能对话智能体易偏离用户意图的问题,提出“用户即工具”的插入扩展交互概念,并通过两项实证研究验证了该方法在推荐领域的有效性。

摘要:

本文深入探讨了大型语言模型中思维链提示的一种高级实现,重点关注在该提示方法生成的显式推理路径内使用工具(或“插件”)。我们发现,工具赋能对话智能体常常偏离主题,因为来自搜索引擎或计算器等工具的额外上下文转移了原始用户意图。为了解决这一问题,我们探索了一种概念,即用户本身成为工具,提供必要细节并细化其请求。通过对话分析,我们将这种交互刻画为插入扩展——一种旨在促成首选回应的中介对话。我们在两项使用直接比较的实证研究中探索了这种“用户即工具”方法所产生的可能性,并发现其在推荐领域具有优势。

英文摘要:

This paper delves into an advanced implementation of Chain-of-Thought-Prompting in Large Language Models, focusing on the use of tools (or "plug-ins") within the explicit reasoning paths generated by this prompting method. We find that tool-enabled conversational agents often become sidetracked, as additional context from tools like search engines or calculators diverts from original user intents. To address this, we explore a concept wherein the user becomes the tool, providing necessary details and refining their requests. Through Conversation Analysis, we characterize this interaction as insert-expansion - an intermediary conversation designed to facilitate the preferred response. We explore possibilities arising from this 'user-as-a-tool' approach in two empirical studies using direct comparison, and find benefits in the recommendation domain.

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。

↑