@inproceedings{zou-etal-2026-emores,
    title = "{E}mo{R}es: Toward Adaptive Psychological Support via User-Agnostic Benchmark and Topic-Mining Agent",
    author = "Zou, Zhengwei  and
      Jiang, Xuanming  and
      An, Baoyi  and
      Nie, Dingyu  and
      Fang, Zhengxing  and
      Liu, Qingyu  and
      Qian, Xueming  and
      Zhao, Guoshuai  and
      Yang, Zhongyu",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.416/",
    pages = "8575--8586",
    ISBN = "979-8-89176-395-1",
    abstract = "Large language models exhibit significant potential for psychological support, yet they often generate fragmented and emotionally inconsistent dialogues that lack the therapeutic structure necessary for reliable assessment.To address these issues, we introduce **VeilEval**, a clinically grounded and privacy-preserving benchmark equipped with interpretable metrics for evaluating multi-turn psychological dialogues.Furthermore, we propose Emotion-Resonance (**EmoRes**), a multi-agent framework that boosts psychological reasoning via a Topic-Mining Emotional Agent and a multi-perspective Self-Reflection Agent, thereby jointly improving topic continuity, emotional coherence, and clinical interpretability.Experiments demonstrate that EmoRes achieves up to $\sim 3\times$ improvement over strong baselines on VeilEval, with its effectiveness further validated by ablation studies and human evaluations."
}