arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.13481cs.AI
收藏

通过多智能体指令细化实现高效的稳健语言情绪诊断以促进心理健康

Towards Efficient and Robust Linguistic Emotion Diagnosis for Mental Health via Multi-Agent Instruction Refinement

School of Computer Science and Technology, Xi’an Jiaotong University（计算机科学与技术学院，西安交通大学）；Saw Swee Hock School of Public Health, National University of Singapore（Saw Swee Hock 公共卫生学院，新加坡国立大学）

Jian Zhang, Zhangqi Wang, Zhiyuan Wang, Weiping Fu, Yu He, Haiping Zhu, Qika Lin, Jun Liu

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

APOLO通过多智能体协作优化提示空间，提升语言情绪诊断的效率与鲁棒性，适用于心理健康领域的可信LLM应用。

摘要：

语言表达的情绪，如抑郁、焦虑和创伤相关状态，在临床笔记、咨询对话和在线心理健康社区中普遍存在，准确识别这些情绪对于临床分诊、风险评估和及时干预至关重要。尽管大型语言模型（LLMs）在情绪分析任务中表现出强大的泛化能力，但其在高风险、情境密集的医疗环境中的诊断可靠性高度敏感于提示设计。此外，现有方法面临两个关键挑战：情绪共病，即多种交织的情绪状态使预测复杂化，以及对临床相关线索的低效探索。为了解决这些挑战，我们提出了APOLO（用于语言情绪诊断的自动提示优化），一个系统探索更广泛和更细粒度提示空间的框架，以提高诊断效率和鲁棒性。APOLO将指令细化建模为部分可观测马尔可夫决策过程，并采用包含规划者、教师、批评者、学生和目标角色的多智能体协作机制。在此闭环框架中，规划者定义优化轨迹，而教师-批评者-学生代理迭代细化提示以增强推理稳定性与有效性，目标代理根据性能评估决定是否继续优化。实验结果表明，APOLO在领域特定和分层基准上一致提高了诊断准确性和鲁棒性，展示了可扩展且通用的可信LLM在心理健康护理中的应用范式。

英文摘要：

Linguistic expressions of emotions such as depression, anxiety, and trauma-related states are pervasive in clinical notes, counseling dialogues, and online mental health communities, and accurate recognition of these emotions is essential for clinical triage, risk assessment, and timely intervention. Although large language models (LLMs) have demonstrated strong generalization ability in emotion analysis tasks, their diagnostic reliability in high-stakes, context-intensive medical settings remains highly sensitive to prompt design. Moreover, existing methods face two key challenges: emotional comorbidity, in which multiple intertwined emotional states complicate prediction, and inefficient exploration of clinically relevant cues. To address these challenges, we propose APOLO (Automated Prompt Optimization for Linguistic Emotion Diagnosis), a framework that systematically explores a broader and finer-grained prompt space to improve diagnostic efficiency and robustness. APOLO formulates instruction refinement as a Partially Observable Markov Decision Process and adopts a multi-agent collaboration mechanism involving Planner, Teacher, Critic, Student, and Target roles. Within this closed-loop framework, the Planner defines an optimization trajectory, while the Teacher-Critic-Student agents iteratively refine prompts to enhance reasoning stability and effectiveness, and the Target agent determines whether to continue optimization based on performance evaluation. Experimental results show that APOLO consistently improves diagnostic accuracy and robustness across domain-specific and stratified benchmarks, demonstrating a scalable and generalizable paradigm for trustworthy LLM applications in mental healthcare.

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。

↑