Saved in:
Bibliographic Details
Main Authors: Teng, Shiyu, Liu, Jiaqing, Sun, Hao, Li, Yu, Chai, Shurong, Hou, Ruibo, Tateyama, Tomoko, Lin, Lanfen, Chen, Yen-Wei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.11334
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918442802610176
author Teng, Shiyu
Liu, Jiaqing
Sun, Hao
Li, Yu
Chai, Shurong
Hou, Ruibo
Tateyama, Tomoko
Lin, Lanfen
Chen, Yen-Wei
author_facet Teng, Shiyu
Liu, Jiaqing
Sun, Hao
Li, Yu
Chai, Shurong
Hou, Ruibo
Tateyama, Tomoko
Lin, Lanfen
Chen, Yen-Wei
contents Depression remains widely underdiagnosed and undertreated because stigma and subjective symptom ratings hinder reliable screening. To address this challenge, we propose a coarse-to-fine, multi-stage framework that leverages large language models (LLMs) for accurate and interpretable detection. The pipeline performs binary screening, five-class severity classification, and continuous regression. At each stage, an LLM produces progressively richer clinical summaries that guide a multimodal fusion module integrating text, audio, and video features, yielding predictions with transparent rationale. The system then consolidates all summaries into a concise, human-readable assessment report. Experiments on the E-DAIC and CMDC datasets show significant improvements over state-of-the-art baselines in both accuracy and interpretability.
format Preprint
id arxiv_https___arxiv_org_abs_2604_11334
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Dynamic Summary Generation for Interpretable Multimodal Depression Detection
Teng, Shiyu
Liu, Jiaqing
Sun, Hao
Li, Yu
Chai, Shurong
Hou, Ruibo
Tateyama, Tomoko
Lin, Lanfen
Chen, Yen-Wei
Artificial Intelligence
Depression remains widely underdiagnosed and undertreated because stigma and subjective symptom ratings hinder reliable screening. To address this challenge, we propose a coarse-to-fine, multi-stage framework that leverages large language models (LLMs) for accurate and interpretable detection. The pipeline performs binary screening, five-class severity classification, and continuous regression. At each stage, an LLM produces progressively richer clinical summaries that guide a multimodal fusion module integrating text, audio, and video features, yielding predictions with transparent rationale. The system then consolidates all summaries into a concise, human-readable assessment report. Experiments on the E-DAIC and CMDC datasets show significant improvements over state-of-the-art baselines in both accuracy and interpretability.
title Dynamic Summary Generation for Interpretable Multimodal Depression Detection
topic Artificial Intelligence
url https://arxiv.org/abs/2604.11334