Lune

ACL Findings2026

Emotion Trajectory-aware Retrieval for Markov-driven Emotion Anticipation in LLM-based Emotional Support Conversation

Hongyan Wu, Zhiliang Tian, Zhen Huang, Tengyue Hu, Linbo Qiao, Yifu Gao, Feng Liu, Dongsheng Li

Abstract

Emotional support conversation (ESC) aims to alleviate users' psychological stress. Selecting the appropriate strategy is crucial for effective emotional support. Current strategy plannerbased methods prioritize immediate responses while neglecting users' future reactions. Some studies retrieve historical examples with similar emotions to the current utterance, then anticipating future emotions based on next-turn emotions of historical examples. However, their retrievals focus on the current emotion (i.e. a single-turn emotion state), while they ignore the evolution of user's emotion before the current state. We argue that retrievals considering the whole emotional trajectories enables models to capture the dynamic emotional needs, thereby enhancing the anticipation of future emotions. To this end, we propose Markovdriven emotion anticipation framework with emotion trajectory-aware retrieval for LLMbased ESC, which anticipates future emotion states to guide strategy planning and achieve sustained emotional support. First, we construct a dynamic emotion memory and perform hierarchical retrieval that combines semantic matching and emotion trajectory alignment. Then, we model emotional transitions as Markov chains, leveraging trajectory-aware retrieval to estimate future emotion. Finally, we use the anticipated emotion to steer LLMs in generating candidate strategies and introduce active online learning to optimize the planner, boosting its robustness on diverse users. Experiments on two datasets with two models shows that our method excels all baselines.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations cites MISC: A Mixed Strategy-Aware Model integrating COMET for Emotional Support Conversation
  • SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations cites Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning
  • Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents cites Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning
  • Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning cites MISC: A Mixed Strategy-Aware Model integrating COMET for Emotional Support Conversation
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on22

  1. MISC: A Mixed Strategy-Aware Model integrating COMET for Emotional Support ConversationQuan Tu, Yanran Li, Jianwei Cui, Bin Wang et al.ACL 2022 · 141 citations
  2. Plug-and-Play Policy Planner for Large Language Model Powered Dialogue AgentsYang Deng, Wenxuan Zhang, Wai Lam, See-Kiong Ng et al.ICLR 2024 · 86 citations
  3. SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy ConversationsYirong Chen, Xiaofen Xing, Jingkai Lin, Huimin Zheng et al.EMNLP Findings 2023 · 81 citations
  4. Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaborationYang Deng, Lizi Liao, Liang Chen, Hongru Wang et al.EMNLP Findings 2023 · 55 citations
  5. Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy PlanningYi Cheng, Wenge Liu, Wenjie Li, Jiashuo Wang et al.EMNLP 2022 · 32 citations

Related papers

  1. ESCA: An Emotional Support Conversation Agent for Enhancing Reasonable Strategy Planning and Effective ExpressionJing Li, Yanxin Luo, Donghong Han, Yimeng Zhan et al.AAAI 2026
  2. Detecting Emotional Dynamic Trajectories: An Evaluation Framework for Emotional Support in Language ModelsZhouxing Tan, Ruochong Xiong, Yulong Wan, Jinlong Ma et al.AAAI 2026
  3. Facilitating Multi-turn Emotional Support Conversation with Positive Emotion Elicitation: A Reinforcement Learning ApproachJinfeng Zhou, Zhuang Chen, Bo Wang, Minlie HuangACL 2023 · 17 citations
  4. Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support ConversationDongjin Kang, Sunghwan Kim, Taeyoon Kwon, Seungjun Moon et al.ACL 2024 · 14 citations
  5. TransESC: Smoothing Emotional Support Conversation via Turn-Level State TransitionWeixiang Zhao, Yanyan Zhao, Shilong Wang, Bing QinACL Findings 2023 · 23 citations
Dusk over the sea between two cliffs drawn in fine vertical lines