Thoughts to target : enhance planning for target-driven conversation

• Main Authors: ZHENG, Zhonghua, LIAO, Lizi, DENG, Yang, LIM, Ee-peng, HUANG, Minlie, NIE, Liqiang
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Conversational AI; Conversation planning; Large Language Models; LLMS; Artificial Intelligence and Robotics; Computer Sciences
• Online Access: https://ink.library.smu.edu.sg/sis_research/9564
• Institution: Singapore Management University

In conversational AI, large-scale models excel in various tasks but struggle with target-driven conversation planning. Current methods, such as chain-of-thought reasoning and tree-search policy learning techniques, either neglect plan rationality or require extensive human simulation procedures. Add...