Kardia-R1: 通过Rubric-as-Judge强化学习释放大语言模型以通过评分标准进行推理，以实现情感支持的理解与共情
Kardia-R1: Unleashing LLMs to Reason toward Understanding and Empathy for Emotional Support via Rubric-as-Judge Reinforcement Learning
AI总结：
Kardia-R1通过Rubric-as-Judge强化学习框架，提升大语言模型在情感支持中的理解与共情能力，通过评分标准引导训练以实现更准确的情感推理和个性化响应。
摘要：
随着网络平台朝着更个性化和情感复杂性发展，对话代理必须超越表面共情，展示具有身份意识的情感推理。然而，现有系统面临两个限制：(1) 依赖于以情境为中心的数据集，缺乏持久的用户身份，这阻碍了个性化情感细微差别的捕捉；(2) 依赖于不透明、粗粒度的奖励信号，阻碍了可验证的共情推理的发展。为了解决这些差距，我们引入了KardiaBench，一个大规模的用户基础基准，包含178,080个问答对，涵盖22,080个多轮对话，这些对话基于671个真实世界档案。该数据集通过一个模型在循环中的管道进行构建，通过迭代的评分标准引导细化来确保心理合理性和个人身份一致性。这种逐步共情的管道将用户理解、上下文推理和情感感知整合到对话中，随后通过迭代批评和基于评分标准的细化来确保心理合理性和情感真实性和个人身份一致性。在此基础上，我们提出了Kardia-R1，一个训练模型进行可解释、逐步共情认知的框架。Kardia-R1利用Rubric-as-Judge Empathetic Reinforcement Learning（Rubric-ERL），一种基于GRPO的方法，利用可解释、与人类对齐的评分标准奖励，紧密连接用户理解、情感推断和支持性响应生成。在四个LLM基础架构上的广泛实验表明，Kardia-R1在情绪准确性、共情、相关性、个人身份一致性和安全性方面始终优于其他方法。我们的数据集和模型将在https://github.com/JhCircle/Kardia-R1上发布。
英文摘要：
As web platforms evolve towards greater personalization and emotional complexity, conversational agents must transcend superficial empathy to demonstrate identity-aware emotional reasoning. However, existing systems face two limitations: (1) reliance on situation-centric datasets lacking persistent user identity, which hampers the capture of personalized affective nuances; and (2) dependence on opaque, coarse reward signals that hinder development of verifiable empathetic reasoning. To address these gaps, we introduce KardiaBench, a large-scale user-grounded benchmark comprising 178,080 QA pairs across 22,080 multi-turn conversations anchored to 671 real-world profiles. The dataset is constructed via a model-in-the-loop pipeline with iterative rubric-guided refinement to ensure psychological plausibility and persona consistency. This progressive empathy pipeline that integrates user comprehension, contextual reasoning, and emotion perception into conversations, followed by iterative critique and rubric-based refinement to ensure psychological plausibility, emotional fidelity, and persona consistency. Building on this, we propose Kardia-R1, a framework that trains models for interpretable, stepwise empathetic cognition. Kardia-R1 leverages Rubric-as-Judge Empathetic Reinforcement Learning (Rubric-ERL), a GRPO-based method that uses explainable, human-aligned rubric rewards to tightly couple user understanding, emotional inference, and supportive response generation. Extensive experiments across four LLM backbones demonstrate that Kardia-R1 consistently outperforms othet methods in emotion accuracy, empathy, relevance, persona consistency, and safety. Our dataset and model will be released at https://github.com/JhCircle/Kardia-R1.
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。
