Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

8-2024

Abstract

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 elaborate prompt engineering to the integration of policy networks, either face efficiency issues or deliver suboptimal performance. Inspired by the dual-process theory in psychology, which identifies two distinct modes of thinking—intuitive (fast) and analytical (slow), we propose the Dual-Process Dialogue Planning (DPDP) framework. DPDP embodies this theory through two complementary planning systems: an instinctive policy model for familiar contexts and a deliberative Monte Carlo Tree Search (MCTS) mechanism for complex, novel scenarios. This dual strategy is further coupled with a novel two-stage training regimen: offline Reinforcement Learning for robust initial policy model formation followed by MCTS-enhanced on-the-fly learning, which ensures a dynamic balance between efficiency and strategic depth. Our empirical evaluations across diverse dialogue tasks affirm DPDP’s superiority in achieving both high-quality dialogues and operational efficiency, outpacing existing methods.

Keywords

Large Language Models, LLMs, Dual-Process Dialogue Planning framework, Natural language processing

Discipline

Artificial Intelligence and Robotics | Computer Sciences

Research Areas

Data Science and Engineering; Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

Proceedings of 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) : Bangkok, Thailand, August 11-16

Volume

1

First Page

4768

Last Page

4791

Identifier

10.18653/v1/2024.acl-long.262

Publisher

Association for Computational Linguistics

City or Country

Bangkok, Thailand

Additional URL

https://doi.org/10.18653/v1/2024.acl-long.262

Download

Share

COinS