@inproceedings{he-etal-2024-planning,
title = "Planning Like Human: A Dual-process Framework for Dialogue Planning",
author = "He, Tao and
Liao, Lizi and
Cao, Yixin and
Liu, Yuanxing and
Liu, Ming and
Chen, Zerui and
Qin, Bing",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.luhme-long.262/",
doi = "10.18653/v1/2024.acl-long.262",
pages = "4768--4791",
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."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-etal-2024-planning">
<titleInfo>
<title>Planning Like Human: A Dual-process Framework for Dialogue Planning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lizi</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixin</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanxing</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zerui</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">he-etal-2024-planning</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.262</identifier>
<location>
<url>https://aclanthology.org/2024.luhme-long.262/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>4768</start>
<end>4791</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Planning Like Human: A Dual-process Framework for Dialogue Planning
%A He, Tao
%A Liao, Lizi
%A Cao, Yixin
%A Liu, Yuanxing
%A Liu, Ming
%A Chen, Zerui
%A Qin, Bing
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F he-etal-2024-planning
%X 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.
%R 10.18653/v1/2024.acl-long.262
%U https://aclanthology.org/2024.luhme-long.262/
%U https://doi.org/10.18653/v1/2024.acl-long.262
%P 4768-4791
Markdown (Informal)
[Planning Like Human: A Dual-process Framework for Dialogue Planning](https://aclanthology.org/2024.luhme-long.262/) (He et al., ACL 2024)
ACL
- Tao He, Lizi Liao, Yixin Cao, Yuanxing Liu, Ming Liu, Zerui Chen, and Bing Qin. 2024. Planning Like Human: A Dual-process Framework for Dialogue Planning. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4768–4791, Bangkok, Thailand. Association for Computational Linguistics.