@inproceedings{haydarov-etal-2025-towards,
    title = "Towards {AI}-Assisted Psychotherapy: Emotion-Guided Generative Interventions",
    author = "Haydarov, Kilichbek  and
      Mohamed, Youssef  and
      Goldenhersch, Emilio  and
      OCallaghan, Paul  and
      Li, Li-jia  and
      Elhoseiny, Mohamed",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1664/",
    pages = "32724--32743",
    ISBN = "979-8-89176-332-6",
    abstract = "Large language models (LLMs) hold promise for therapeutic interventions, yet most existing datasets rely solely on text, overlooking non-verbal emotional cues essential to real-world therapy. To address this, we introduce a multimodal dataset of 1,441 publicly sourced therapy session videos containing both dialogue and non-verbal signals such as facial expressions and vocal tone. Inspired by Hochschild{'}s concept of emotional labor, we propose a computational formulation of \textit{emotional dissonance}{---}the mismatch between facial and vocal emotion{---}and use it to guide emotionally aware prompting. Our experiments show that integrating multimodal cues, especially dissonance, improves the quality of generated interventions. We also find that LLM-based evaluators misalign with expert assessments in this domain, highlighting the need for human-centered evaluation. Data and code will be released to support future research."
}