Skip to main navigation Skip to search Skip to main content

STRIDE-ED: A Strategy-Grounded Stepwise Reasoning Framework for Empathetic Dialogue Systems

  • Hongru Ji
  • , Yuyin Fan
  • , Meng Zhao
  • , Xianghua Li
  • , Lianwei Wu
  • , Chao Gao
  • Northwestern Polytechnical University Xian
  • Henan University of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Empathetic dialogue requires not only recognizing a user's emotional state but also making strategy-aware, context-sensitive decisions throughout response generation. However, the lack of a comprehensive empathy strategy framework, explicit task-aligned multi-stage reasoning, and high-quality strategy-aware data fundamentally limits existing approaches, preventing them from effectively modeling empathetic dialogue as a complex, multi-stage cognitive and decision-making process. To address these challenges, we propose STRIDE-ED, a STRategy-grounded, Interpretable, and DEep reasoning framework that models Empathetic Dialogue through structured, strategy-conditioned reasoning. To support effective learning, we develop a strategy-aware data refinement pipeline integrating LLM-based annotation, multi-model consistency-weighted evaluation, and dynamic sampling to construct high-quality training data aligned with empathetic strategies. Furthermore, we adopt a two-stage training paradigm that combines supervised fine-tuning with multi-objective reinforcement learning to better align model behaviors with target emotions, empathetic strategies, and response formats. Extensive experiments demonstrate that STRIDE-ED generalizes across diverse open-source LLMs and consistently outperforms existing methods on both automatic metrics and human evaluations.

Original languageEnglish
Title of host publicationLong Papers
EditorsMaria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
PublisherAssociation for Computational Linguistics (ACL)
Pages7088-7102
Number of pages15
ISBN (Electronic)9798891763906
DOIs
StatePublished - 2026
Event64th Annual Meeting of the Association for Computational Linguistics, ACL 2026 - San Diego, United States
Duration: 2 Jul 2026 → 7 Jul 2026

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
Volume1
ISSN (Print)0736-587X

Conference

Conference64th Annual Meeting of the Association for Computational Linguistics, ACL 2026
Country/TerritoryUnited States
CitySan Diego
Period2/07/26 → 7/07/26

Fingerprint

Dive into the research topics of 'STRIDE-ED: A Strategy-Grounded Stepwise Reasoning Framework for Empathetic Dialogue Systems'. Together they form a unique fingerprint.

Cite this