Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration

Yang Deng, Lizi Liao, Liang CHEN, Hongru WANG, Wenqiang Lei, Tat-Seng Chua

Submission Type: Regular Long Paper

Submission Track: Dialogue and Interactive Systems

Keywords: Proactive Dialogue, Asking Clarification Question, Target-guided Conversation

Abstract: Conversational systems based on Large Language Models (LLMs), such as ChatGPT, show exceptional proficiency in context understanding and response generation. However, they still possess limitations, such as failing to ask clarifying questions to ambiguous queries or refuse users' unreasonable requests, both of which are considered as key aspects of a conversational agent's proactivity. This raises the question of whether LLM-based conversational systems are equipped to handle proactive dialogue problems. In this work, we conduct a comprehensive analysis of LLM-based conversational systems, specifically focusing on three key aspects of proactive dialogues: clarification, target-guided, and non-collaborative dialogues. To trigger the proactivity of LLMs, we propose the Proactive Chain-of-Thought prompting scheme, which augments LLMs with the goal planning capability over descriptive reasoning chains. Empirical findings are discussed to promote future studies on LLM-based proactive dialogue systems.

Submission Number: 2571