@inproceedings{zhao-etal-2025-chain,
    title = "Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter",
    author = "Zhao, Weixiang  and
      Sui, Xingyu  and
      Han, Xinyang  and
      Deng, Yang  and
      Hu, Yulin  and
      Guo, Jiahe  and
      Qin, Libo  and
      Du, Qianyun  and
      Wang, Shijin  and
      Zhao, Yanyan  and
      Qin, Bing  and
      Liu, Ting",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.831/",
    doi = "10.18653/v1/2025.findings-emnlp.831",
    pages = "15361--15381",
    ISBN = "979-8-89176-335-7",
    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."
}