arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2310.03293cs.CL
收藏

一种通过提问检测用户意图的大语言模型对话响应生成新智能体

A New Dialogue Response Generation Agent for Large Language Models by Asking Questions to Detect User's Intentions

School of Computer Science and Engineering(计算机科学与工程学院);Nanjing University of Science and Technology(南京理工大学)

Siwei Wu, Xiangqing Shen, Rui Xia

AI总结:

针对大语言模型在对话中易忽略用户隐含意图、领域知识不全且更新不及时的问题,提出EDIT框架,通过生成开放式问题检测隐含意图,结合大语言模型和领域知识库获取额外知识以增强响应生成,还构建了COQ数据集,在两个对话任务上表现更优。

摘要:

大语言模型(LLMs),例如ChatGPT,凭借其开放域生成能力,近期已被应用于各类自然语言处理(NLP)任务。然而,将大语言模型应用于对话任务存在两个问题。1. 在对话过程中,用户可能存在被大语言模型忽略的隐含意图,导致生成的响应无法与用户意图对齐。2. 大语言模型不可能全面覆盖所有领域,在某些特定领域其知识可能存在缺失,且无法实时更新最新知识。为解决这些问题,我们提出了一个框架——**利用大语言模型通过提问检测用户隐含意图来增强对话响应生成**(**EDIT**,全称为using LLM to Enhance dialogue response generation by asking questions to Detect user's Implicit inTentions)。首先,EDIT生成与对话上下文相关的开放式问题,作为潜在的用户意图;然后,EDIT分别通过与大语言模型交互、在领域特定知识库中搜索来回答这些问题,并利用大语言模型选取合适的问题答案作为额外知识;最后,EDIT通过显式整合这些额外知识来增强响应生成。此外,以往的问题生成研究仅关注提出答案在上下文中的问题。为了生成开放式问题,我们构建了上下文-开放式问题(COQ)数据集。在两个任务导向型对话任务(Wizard of Wikipedia和Holl-E)上,EDIT的表现优于其他大语言模型。

英文摘要:

Large Language Models (LLMs), such as ChatGPT, have recently been applied to various NLP tasks due to its open-domain generation capabilities. However, there are two issues with applying LLMs to dialogue tasks. 1. During the dialogue process, users may have implicit intentions that might be overlooked by LLMs. Consequently, generated responses couldn't align with the user's intentions. 2. It is unlikely for LLMs to encompass all fields comprehensively. In certain specific domains, their knowledge may be incomplete, and LLMs cannot update the latest knowledge in real-time. To tackle these issues, we propose a framework~\emph{using LLM to \textbf{E}nhance dialogue response generation by asking questions to \textbf{D}etect user's \textbf{I}mplicit in\textbf{T}entions} (\textbf{EDIT}). Firstly, EDIT generates open questions related to the dialogue context as the potential user's intention; Then, EDIT answers those questions by interacting with LLMs and searching in domain-specific knowledge bases respectively, and use LLMs to choose the proper answers to questions as extra knowledge; Finally, EDIT enhances response generation by explicitly integrating those extra knowledge. Besides, previous question generation works only focus on asking questions with answers in context. In order to ask open questions, we construct a Context-Open-Question (COQ) dataset. On two task-oriented dialogue tasks (Wizard of Wikipedia and Holl-E), EDIT outperformed other LLMs.

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。

↑