AudiPsy: Evidence-Grounded Multimodal Reasoning over Spoken Counseling Conversations for Depression Assessment

Text-based counseling provides a valuable source of information for assessing depression severity. We study prediction of the total score on the eight-item Patient Health Questionnaire (PHQ-8), a self-report measure of depression severity, from counseling transcripts. Clinical-based methods rely mainly on large language model (LLM) inference to obtain structured session-level assessments, but these assessments provide limited information about which utterances support each score. Training-based methods train predictors directly on sentences or their semantic embeddings and preserve local conversational detail, but must learn clinical structure from limited labeled transcripts. Integrating a small set of clinical feature scores with a long sequence of high-dimensional utterance representations is challenging, as simple fusion can overemphasize dialogue evidence and fail to link clinical features to supporting utterances. Combining structured clinical assessments with sentence-level semantics, we propose EmoTrack, which jointly encodes clinical feature scores and utterance representations to predict the total PHQ-8 score. For longitudinal assessment across successive sessions, the model can also incorporate a compressed representation of the preceding session as optional memory. On the real-world DAIC-WOZ benchmark, EmoTrack reduces mean absolute error from 2.8234 to 2.4708 relative to the strongest evaluated baseline. Across five settings covering single-session estimation, cross-dataset transfer without adaptation, and longitudinal assessment, it reduces normalized aggregate error by approximately 6.1% relative to the strongest baseline.

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.

Automatic Depression Detection (ADD) from clinical interviews is a pivotal task in computational mental health, yet it remains challenging due to two critical obstacles: 1) difficulty in modeling complex but sparsely distributed depression clues within lengthy, multi-topic clinical interviews, leading to superficial and unreliable reasoning; 2) scarcity of labeled data due to clinical privacy, together with high cost of training and fine-tuning, limiting the deployment of supervised ADD systems. To jointly address these challenges, we propose Dep-LLM, a training-free framework that mirrors the step-by-step reasoning of clinical psychiatrists and operates entirely on frozen off-the-shelf foundation LLMs. Dep-LLM comprises three stages. First, a Chain-of-Thought (CoT) Depression Multi-factor Analysis module structurally decomposes the long dialogue into five clinically aligned themes and produces evidence-grounded rationales, effectively handling long-context dependencies. Second, we introduce Confidence Analysis and Modulation module that quantifies the epistemic reliability from token-level entropy of each rationale and applies an intra-label and inter-theme modulation that amplifies trustworthy signals while suppressing uncertain ones without extra training. Third, a Collaborative Multi-factor Prediction module dynamically integrates multi-factor signals weighted by confidence into the final diagnosis. Extensive experiments on the DAIC-WOZ and E-DAIC datasets demonstrate the effectiveness and generalizability of Dep-LLM: it surpasses zero-shot baseline on nearly all 21 foundation LLMs across 9 metrics such as accuracy, macro F1 and weighted-average F1, and further outperforms state-of-the-art supervised domain-specific LLMs as well as the latest closed-source commercial LLMs, while requiring no extra training.