Skip to main navigation Skip to search Skip to main content

Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter

  • Weixiang Zhao
  • , Xingyu Sui
  • , Xinyang Han
  • , Yang Deng
  • , Yulin Hu
  • , Jiahe Guo
  • , Libo Qin
  • , Qianyun Du
  • , Shijin Wang
  • , Yanyan Zhao*
  • , Bing Qin
  • , Ting Liu
  • *Corresponding author for this work
  • Harbin Institute of Technology
  • Singapore Management University
  • Central South University
  • IFLYTEK Co., Ltd.

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The growing emotional stress in modern society has increased the demand for Emotional Support Conversations (ESC). While Large Language Models (LLMs) show promise for ESC, they face two key challenges: (1) low strategy selection accuracy, and (2) preference bias, limiting their adaptability to users’ emotional needs. Existing supervised fine-tuning (SFT) struggles to address these issues, as it rigidly trains models on single gold-standard responses without modeling nuanced strategy trade-offs. To overcome these limitations, we propose a novel two-stage framework that optimizes strategy selection preferences at each dialogue turn. We first leverage Monte Carlo Tree Search to construct ESC-Pro, a high-quality preference dataset with turn-level strategy-response pairs. Then training on ESC-Pro with Chain-of-Strategy Optimization (CSO) improves both strategy accuracy and bias mitigation, enabling LLMs to generate more empathetic and contextually appropriate responses. Experiments on LLaMA-3.1-8B, Gemma-2-9B, and Qwen2.5-7B demonstrate that CSO outperforms standard SFT, highlighting the efficacy of fine-grained, turn-level preference modeling in ESC.1

Original languageEnglish
Title of host publicationEMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2025
EditorsChristos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
PublisherAssociation for Computational Linguistics (ACL)
Pages15361-15381
Number of pages21
ISBN (Electronic)9798891763357
DOIs
StatePublished - 2025
Event30th Conference on Empirical Methods in Natural Language Processing, EMNLP 2025 - Suzhou, China
Duration: 4 Nov 20259 Nov 2025

Publication series

NameEMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2025

Conference

Conference30th Conference on Empirical Methods in Natural Language Processing, EMNLP 2025
Country/TerritoryChina
CitySuzhou
Period4/11/259/11/25

Fingerprint

Dive into the research topics of 'Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter'. Together they form a unique fingerprint.

Cite this