@inproceedings{kumar-etal-2026-theory,
    title = "Theory-Explicit Prompting for {MIND} Self-States: Hierarchical {LLM}s and Dynamic Signature Extraction in Mental Health Timelines",
    author = "Kumar, Pawan  and
      Meshram, Ankit  and
      Jha, Shubham  and
      Singh, Loitongbam",
    editor = "Zirikly, Aya  and
      Bar, Kfir  and
      MacAvaney, Sean  and
      Ireland, Molly  and
      Ophir, Yaakov  and
      Atzil-Slonim, Dana  and
      Varadarajan, Vasudha  and
      Bedrick, Steven  and
      Desmet, Bart",
    booktitle = "Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology ({CLP}sych 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.clpsych-1.45/",
    pages = "547--553",
    ISBN = "979-8-89176-421-7",
    abstract = "This paper presents a system for the CLPsych 2026 Shared Task on longitudinal mental health modeling from social media timelines, grounded in the MIND framework. MIND conceptualizes mental health as evolving self-states defined by Affect, Behavior, Cognition, and Desire (ABCD), providing a structured lens on mental health trajectories. The system centers on a theory-explicit prompting framework for structured sequence summarization (Task 3.1) and recurrent dynamic signature extraction (Task 3.2), encoding the full ABCD taxonomy directly into the LLM prompt to ensure clinically grounded, interpretable outputs. A three-stage pipeline infers a direction-of-change label per sequence, produces structured ABCD summaries with few-shot exemplar augmentation, and aggregates these summaries to derive cross-individual recurrent patterns. The system ranks first on deterioration-related recurrent signatures and second overall, achieving the top Fit and Specificity scores in Task 3.2, demonstrating the benefits of explicit clinical grounding for conceptual accuracy."
}