Rethinking conversational agents in the era of large language models: Proactivity, non-collaborativity, and beyond

• Main Authors: DENG, Yang, LEI, Wenqiang, HUANG, Minlie, CHUA, Tat-Seng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Conversational agents; Conversational information seeking; Conversational systems; Human users; Information seeking; Language model; Open-domain dialog; Proactivity; Task-oriented; Task-oriented dialog; Databases and Information Systems; Information Security
• Online Access: https://ink.library.smu.edu.sg/sis_research/9110; https://ink.library.smu.edu.sg/context/sis_research/article/10113/viewcontent/Rethinking.pdf
• Institution: Singapore Management University

Conversational systems are designed to offer human users social support or functional services through natural language interactions. Typical conversation researches mainly focus on the response-ability of the system, such as dialogue context understanding and response generation. In the era of large language models (LLMs), LLM-augmented conversational systems showcase exceptional capabilities of responding to user queries for different language tasks. However, as LLMs are trained to follow users' instructions, LLM-augmented conversational systems typically overlook the design of an essential property in intelligent conversations, i.e., goal awareness. In this tutorial, we will introduce the recent advances on the design of agent's awareness of goals in a wide range of conversational systems, including proactive, non-collaborative, and multi-goal conversational systems. In addition, we will discuss the main open challenges in developing agent's goal awareness in LLM-augmented conversational systems and several potential research directions for future studies.