@inproceedings{chu-etal-2026-beyond,
    title = "Beyond Semantic Similarity: Appraisal-Guided Chain-of-Thought Reasoning and Retrieval for Multimodal Emotional Support Conversations",
    author = "Chu, Yuqi  and
      Liao, Lizi  and
      Liang, Jinggui  and
      Li, Boyang  and
      Hong, Richang",
    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.844/",
    pages = "17104--17119",
    ISBN = "979-8-89176-395-1",
    abstract = "Emotional support conversation systems strive to emulate the empathetic depth of human therapists, yet current approaches often fail due to the ``Cognitive Gap''{---}the inability to discern the latent psychological evaluations driving a user{'}s distress. Existing retrieval-augmented generation paradigms exacerbate this by relying on semantic similarity, frequently retrieving historical dialogues that are surface analogous but therapeutically incongruent. To bridge this gap, we introduce Appraisal-Guided Chain-of-Thought Reasoning {\&} Retrieval (AG-CTR{\texttwosuperior}) for better emotional support. Specifically, we bootstrap the MLLM to generate appraisal-guided reasoning chains and apply a dual-signal verification mechanism using ground-truth emotion labels and a teacher model to verify and correct them. Under such instance-level guidance, we finetune the MLLM to internalize such reasoning capability. At inference, the model utilizes its generated appraisal chain as a structured query to help retrieve historical therapeutic responses based on psychological situation similarity rather than content surface proximity. Extensive experiments and analyses on two ESC benchmarks demonstrate that AG-CTR{\texttwosuperior} significantly outperforms state-of-the-art baselines."
}