Planning like human : A dual-process framework for dialogue planning

• Main Authors: HE, Tao, LIAO, Lizi, CAO, Yixin, LIU, Yuanxing, LIU, Ming, CHEN, Zerui, QIN, Bing
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Large Language Models; LLMs; Dual-Process Dialogue Planning framework; Natural language processing; Artificial Intelligence and Robotics; Computer Sciences
• Online Access: https://ink.library.smu.edu.sg/sis_research/9696; https://ink.library.smu.edu.sg/context/sis_research/article/10696/viewcontent/2024.acl_long.262.pdf
• Institution: Singapore Management University

In proactive dialogue, the challenge lies not just in generating responses but in steering conversations toward predetermined goals, a task where Large Language Models (LLMs) typically struggle due to their reactive nature. Traditional approaches to enhance dialogue planning in LLMs, ranging from el...