从通用共情到个性化情感支持：一种用于用户偏好对齐的自我进化框架
From Generic Empathy to Personalized Emotional Support: A Self-Evolution Framework for User Preference Alignment
AI总结：
该文提出一种自我进化框架，通过两阶段微调与自我反思精炼及迭代直接偏好优化，使大语言模型在情感支持中更好对齐用户个性、情绪和情境的隐性偏好，减少无用回应并提升支持效果。
摘要：
有效的情感支持依赖于理解用户的情绪和需求，以便在多轮交互中提供有意义的安慰。大型语言模型（LLMs）在表达共情方面显示出巨大潜力；然而，它们常常提供通用且千篇一律的回应，无法满足用户的具体需求。为了解决这一问题，我们提出了一种自我进化框架，旨在帮助LLMs改进其回应，以更好地对齐用户关于用户画像（个性）、情绪状态和具体情境的隐性偏好。我们的框架包含两个不同的阶段：\textit{(1)} \textit{情感支持经验获取}，在此阶段，LLMs在有限的情感支持对话数据上进行微调，以提供基础支持；以及\textit{(2)} \textit{个性化情感支持的自我改进}，在此阶段，LLMs利用自我反思和自我精炼来生成个性化回应。通过在前精炼和后精炼回应之间进行迭代直接偏好优化，我们的模型生成的回应能更好地理解用户的隐性偏好。大量实验和评估表明，我们的方法显著提升了模型在情感支持方面的性能，减少了无帮助的回应，并最小化了用户偏好与模型输出之间的差异。
英文摘要：
Effective emotional support hinges on understanding users' emotions and needs to provide meaningful comfort during multi-turn interactions. Large Language Models (LLMs) show great potential for expressing empathy; however, they often deliver generic and one-size-fits-all responses that fail to address users' specific needs. To tackle this issue, we propose a self-evolution framework designed to help LLMs improve their responses to better align with users' implicit preferences concerning user profiles (personalities), emotional states, and specific situations. Our framework consists of two distinct phases: \textit{(1)} \textit{Emotional Support Experience Acquisition}, where LLMs are fine-tuned on limited emotional support conversation data to provide basic support, and \textit{(2)} \textit{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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
