Thoughts to Target: Enhance Planning for Target-driven Conversation

Zhonghua Zheng, Lizi Liao, Yang Deng, Ee-Peng Lim, Minlie Huang, Liqiang Nie


Abstract
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. Addressing this, we propose a novel two-stage framework, named EnPL, to improve the LLMs’ capability in planning conversations towards designated targets, including (1) distilling natural language plans from target-driven conversation corpus and (2) generating new plans with demonstration-guided in-context learning. Specifically, we first propose a filter approach to distill a high-quality plan dataset, ConvPlan (Resources of this paper can be found at https://github.com/pandazzh2020/ConvPlan). With the aid of corresponding conversational data and support from relevant knowledge bases, we validate the quality and rationality of these plans. Then, these plans are leveraged to help guide LLMs to further plan for new targets. Empirical results demonstrate that our method significantly improves the planning ability of LLMs, especially in target-driven conversations. Furthermore, EnPL is demonstrated to be quite effective in collecting target-driven conversation datasets and enhancing response generation, paving the way for constructing extensive target-driven conversational models.
Anthology ID:
2024.emnlp-main.1175
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
21108–21124
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1175
DOI:
10.18653/v1/2024.emnlp-main.1175
Bibkey:
Cite (ACL):
Zhonghua Zheng, Lizi Liao, Yang Deng, Ee-Peng Lim, Minlie Huang, and Liqiang Nie. 2024. Thoughts to Target: Enhance Planning for Target-driven Conversation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 21108–21124, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Thoughts to Target: Enhance Planning for Target-driven Conversation (Zheng et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1175.pdf