When Symptoms Are Not Enough: Evidence-Weighting Patterns in Large Language Model Psychiatric Screening

• URL: http://arxiv.org/abs/2605.23148v2
• Date: Mon, 25 May 2026 10:34:30 GMT
• Title: When Symptoms Are Not Enough: Evidence-Weighting Patterns in Large Language Model Psychiatric Screening
• Abstract summary: We introduce a SCID-anchored benchmark of 555 semi-structured experiential interviews paired with diagnostic labels for anxiety disorder, major depressive disorder, post-traumatic stress disorder, and any current mental health disorder.<n>We evaluated whether false-negative errors reflected missed psychiatric evidence or differential weighting of symptom, functional-impairment, and protective-context cues.<n>GPT-4.1 Mini and GPT-5 Mini showed the most consistent disorder-specific accuracy.
• Score: 3.840718882315825
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As demand for mental health care outpaces clinician-delivered assessment, scalable screening tools are increasingly needed. Large language models (LLMs) may identify psychiatric risk from patient narratives, but their reliability across diagnoses, demographic subgroups, and evidence-use patterns remains uncertain. We introduce a SCID-anchored benchmark of 555 semi-structured experiential interviews paired with diagnostic reference labels for anxiety disorder, major depressive disorder, post-traumatic stress disorder, and any current mental health disorder. Using zero-shot task-specific prompting, we evaluated five state-of-the-art LLMs and examined whether false-negative errors reflected missed psychiatric evidence or differential weighting of symptom, functional-impairment, and protective-context cues. Performance varied across tasks and models, with accuracy ranging from 0.49 to 0.86 and Matthews correlation coefficients from 0.16 to 0.38. GPT-4.1 Mini and GPT-5 Mini showed the most consistent disorder-specific accuracy. Subgroup analyses found higher depression-classification accuracy among male than female participants, no consistent age-related pattern, and modest non-uniform variation across race strata. Evidence-integration analyses showed that false-negative anxiety and PTSD classifications often contained explicit symptom evidence but were accompanied by preserved functioning, coping ability, or social support. Functional-impairment evidence shifted model outputs toward positive classifications, whereas protective-context evidence shifted outputs away. These findings suggest that LLMs may support scalable psychiatric screening, but their tendency to discount symptom evidence in the presence of preserved functioning or protective context requires careful validation before clinical deployment.

Related papers

• NovGauge: A Fine-Grained Benchmark for Diagnosing LLMs' Capability in Paper Novelty Assessment [54.4265627247104]
  Large language models (LLMs) are increasingly used in peer review at major AI conferences.<n>Existing benchmarks assess novelty as a single holistic score.<n>We present NovGauge, a human-anchored benchmark for fine-grained novelty assessment diagnosis.
  arXiv  Detail & Related papers  (2026-09-10T08:34:56Z)
• Ask Before You Diagnose: Safe-Psych, a Sequential Evaluation Benchmark for LLMs in Psychiatry [2.60905622443275]
  Large language models (LLMs) are increasingly used for decision support in healthcare.<n>Clinical evidence is often incomplete or evolving.<n>We introduce Safe-Psych, a benchmark for evaluating how LLMs handle evolving diagnostic uncertainty.
  arXiv  Detail & Related papers  (2026-05-06T08:52:45Z)
• Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction [72.89352076103889]
  Large language models (LLMs) achieve high accuracy in medical diagnosis when all clinical information is provided in a single turn.<n>We introduce MINT, a high-fidelity, multi-turn medical diagnosis benchmark comprising 1,035 cases.<n>We uncover three persistent behavioral patterns that significantly impact diagnostic decisions.
  arXiv  Detail & Related papers  (2026-04-06T00:23:10Z)
• Agentic Cognitive Profiling: Realigning Automated Alzheimer's Disease Detection with Clinical Construct Validity [66.94391219005291]
  This paper proposes Agentic Cognitive Profiling (ACP), an agentic framework that realigns automated screening with clinical protocol logic.<n>Central to our design is decoupling semantic understanding from measurement by delegating all quantification to deterministic function calling.<n>ACP achieves 90.5% score match rate in task examination and 85.3% accuracy in AD prediction, surpassing popular baselines.
  arXiv  Detail & Related papers  (2026-03-18T06:15:35Z)
• Large Language Models as Simulative Agents for Neurodivergent Adult Psychometric Profiles [0.0]
  Adult neurodivergence, including Attention-Deficit/Hyperactivity Disorder (ADHD), high-functioning Autism Spectrum Disorder (ASD), and Cognitive Disengagement Syndrome (CDS)<n>It remains unclear whether Large Language Models (LLMs) can accurately and stably model neurodevelopmental traits rather than broad personality characteristics.<n>This study examines whether LLMs can generate psychometric responses that approximate those of real individuals when grounded in a structured qualitative interview.
  arXiv  Detail & Related papers  (2026-01-16T10:16:58Z)
• Patterns vs. Patients: Evaluating LLMs against Mental Health Professionals on Personality Disorder Diagnosis through First-Person Narratives [0.0]
  We show that top-performing Gemini Pro models surpassed human professionals in overall diagnostic accuracy by 21.91 percentage points.<n>While both models and human experts excelled at identifying BPD (F1 = 83.4 & F1 = 80.0, respectively), models severely underdiagnosed NPD (F1 = 6.7 vs. 50.0), showing a reluctance toward the value-laden term "narcissism"<n>Our findings demonstrate that while LLMs are highly competent at interpreting complex first-person clinical data, they remain subject to critical reliability and bias issues.
  arXiv  Detail & Related papers  (2025-12-23T12:05:01Z)
• MoodAngels: A Retrieval-augmented Multi-agent Framework for Psychiatry Diagnosis [58.67342568632529]
  MoodAngels is the first specialized multi-agent framework for mood disorder diagnosis.<n>MoodSyn is an open-source dataset of 1,173 synthetic psychiatric cases.
  arXiv  Detail & Related papers  (2025-06-04T09:18:25Z)
• Detecting PTSD in Clinical Interviews: A Comparative Analysis of NLP Methods and Large Language Models [6.916082619621498]
  Post-Traumatic Stress Disorder (PTSD) remains underdiagnosed in clinical settings.<n>This study evaluates natural language processing approaches for detecting PTSD from clinical interview transcripts.
  arXiv  Detail & Related papers  (2025-04-01T22:06:28Z)
• Investigating Large Language Models in Inferring Personality Traits from User Conversations [5.705775078773656]
  Large Language Models (LLMs) are demonstrating remarkable human like capabilities across diverse domains.<n>This study evaluates whether GPT-4o and GPT-4o mini, can infer Big Five personality traits and generate BFI-10 item scores from user conversations.
  arXiv  Detail & Related papers  (2025-01-13T18:09:58Z)
• WellDunn: On the Robustness and Explainability of Language Models and Large Language Models in Identifying Wellness Dimensions [46.60244609728416]
  Language Models (LMs) are being proposed for mental health applications where the heightened risk of adverse outcomes means predictive performance may not be a litmus test of a model's utility in clinical practice. We introduce an evaluation design that focuses on the robustness and explainability of LMs in identifying Wellness Dimensions (WDs) We reveal four surprising results about LMs/LLMs.
  arXiv  Detail & Related papers  (2024-06-17T19:50:40Z)
• Bayesian Networks for the robust and unbiased prediction of depression and its symptoms utilizing speech and multimodal data [65.28160163774274]
  We apply a Bayesian framework to capture the relationships between depression, depression symptoms, and features derived from speech, facial expression and cognitive game data collected at thymia.
  arXiv  Detail & Related papers  (2022-11-09T14:48:13Z)
• Detecting Parkinsonian Tremor from IMU Data Collected In-The-Wild using Deep Multiple-Instance Learning [59.74684475991192]
  Parkinson's Disease (PD) is a slowly evolving neuro-logical disease that affects about 1% of the population above 60 years old. PD symptoms include tremor, rigidity and braykinesia. We present a method for automatically identifying tremorous episodes related to PD, based on IMU signals captured via a smartphone device.
  arXiv  Detail & Related papers  (2020-05-06T09:02:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.