EMNLP Findings2025
From Generic Empathy to Personalized Emotional Support: A Self-Evolution Framework for User Preference Alignment
Abstract
Effective emotional support hinges on understanding users' emotions and needs to provide meaningful comfort during multi-turn interactions. Large Language Models (LLMs) demonstrate significant potential for expressing empathy; however, they often provide generic and one-size-fits-all responses that fail to address users' specific needs. To address this issue, we propose a self-evolution framework designed to help LLMs enhance their responses, aligning them more closely with users' implicit preferences regarding user profiles (personalities), emotional states, and specific situations. Our framework consists of two distinct phases:
(1) Emotional Support Experience Acquisition, where LLMs are fine-tuned on limited emotional support conversation data to provide basic support, and (2) Self-Improvement for Personalized Emotional Support, where LLMs leverage self-reflection and self-refinement to generate personalized responses. Through iterative direct preference optimization between the pre-and post-refined responses, our model generates responses that reflect a better understanding of the user's implicit preferences. Extensive experiments and evaluations demonstrate that our method significantly enhances the model's performance in emotional support, reducing unhelpful responses and minimizing discrepancies between user preferences and model outputs.
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.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Self-Rewarding Language Models cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- EmoHarbor: Evaluating Personalized Emotional Support by Simulating the User's Internal World cites BERTScore: Evaluating Text Generation with BERT
Cited by top-tier papers1
Builds on23
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- Direct Preference Optimization: Your Language Model is Secretly a Reward ModelRafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning et al.NeurIPS 2023 · 10,924 citations
- BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger et al.ICLR 2020 · 8,443 citations
- Self-Refine: Iterative Refinement with Self-FeedbackAman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan et al.NeurIPS 2023 · 4,972 citations
- Self-Rewarding Language ModelsWeizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho, Xian Li et al.ICML 2024 · 569 citations
Related papers
- Look Beyond Feeling: Unveiling Latent Needs from Implicit Expressions for Proactive Emotional SupportXing Fu, Haozhen Li, Bichen Wang, Hao Yang et al.EMNLP 2025 · 1 citation
- 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
- From Personas to Talks: Revisiting the Impact of Personas on LLM-Synthesized Emotional Support ConversationsShenghan Wu, Yimo Zhu, Wynne Hsu, Mong-Li Lee et al.EMNLP 2025 · 1 citation
- Chain of Strategy Optimization Makes Large Language Models Better Emotional SupporterWeixiang Zhao, Xingyu Sui, Xinyang Han, Yang Deng et al.EMNLP Findings 2025 · 1 citation
- I Don't Need Solution. I Need Emotional Support : Empathetic LLMs based on Emotional ValidationSuhyune Son, Jungwoo Lim, Myunghoon Kang, Seongtae Hong et al.ACL Findings 2026
