Explainable depression detection in clinical interviews with personalized retrieval-augmented generation
Open accessAbstract
Depression is a widespread mental health disorder, and clinical interviews are the gold standard for assessment.However, their reliance on scarce professionals highlights the need for automated detection.Current systems mainly employ black-box neural networks, which lack interpretability, which is crucial in mental health contexts.Some attempts to improve interpretability use post-hoc LLM generation but suffer from hallucination.To address these limitations, we propose RED, a Retrievalaugmented generation framework for Explainable depression Detection.RED retrieves evidence from clinical interview transcripts, providing explanations for predictions.Traditional query-based retrieval systems use a one-sizefits-all approach, which may not be optimal for depression detection, as user backgrounds and situations vary.We introduce a personalized query generation module that combines standard queries with user-specific background inferred by LLMs, tailoring retrieval to individual contexts.Additionally, to enhance LLM performance in social intelligence, we augment LLMs by retrieving relevant knowledge from a social intelligence datastore using an eventcentric retriever.Experimental results on the real-world benchmark demonstrate RED's effectiveness compared to neural networks and LLM-based baselines.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the review, twenty studies relied exclusively on closed-source models.
“In our review, twenty studies relied exclusively on closed-source models [62,63,79,89,105,118]”
From Explainability of decoder-only clinical large language models: A scoping review (2026) · cites this paper as [79]
A third, more recent group uses a clinical instrument to organize the reasoning process itself rather than the explanation surface.
“A third, more recent group uses a clinical instrument to organize the reasoning process itself rather than the explanation surface [74,77-79].”
From Explainability of decoder-only clinical large language models: A scoping review (2026) · cites this paper as [79]
Cites
Still being checked.
Cited by
Sorted by citations
Yu, C.-H., & Masum, M. (2026) · Bioengineering · doi:10.3390/bioengineering13010120 · Cited by 10 · see citing works
dos Santos, W. R., Paraboni, I., Matsushima, E. H., Silva, C. A. D., Meira, E. S. D. M., Guimarães, J. V. R. F., Lins, J., Azeredo, L. E. D., Nunes, L. G. C., & Rego, V. T. S. M. (2025) · IEEE Access · doi:10.1109/access.2025.3583259 · Cited by 7 · see citing works
Retrieval‑augmented large language models for depression screening and suicide risk stratification
Xie, W., Song, X., Lu, Z., Fei, G., Zhou, Y., Ding, S., Zuo, F., Wu, B., Gu, T., Xu, L., et al. (2026) · BMC Psychiatry · doi:10.1186/s12888-026-07988-0 · Cited by 6 · see citing works
Wu, Y., Wan, G., Dong, R., Kassam, I. Z., Wiseman, B. C., Rho, J., Graziano, N., Wang, X., Zhang, Y., & Chen, J. (2025) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2025.3634148 · Cited by 1 · see citing works
Natural language processing for mental health assessment: a survey and comparative evaluation
Cao, Y., Xiao, G. G., Xi, P., Okuhara, S., Fan, Y., & Liu, Z. (2026) · International Journal of Data Science and Analytics · doi:10.1007/s41060-026-01146-1 · Cited by 1 · see citing works
Explainability of decoder-only clinical large language models: A scoping review
Mishra, N., Abu-Hanna, A., & Calixto, I. (2026) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2026.103501
Zhao, X., Yang, H., Wang, D., Tang, B., & Zheng, Y. (2025) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2025.3630478
Chowdhury, D., Abdullah, S., Hossain, R., Arefin, M. S., & Hussain, M. M. M. (2026) · International Conference on Sentiment Analysis and Deep Learning (ICSADL) · doi:10.1109/icsadl67539.2026.11452021
Gao, Z., Zhang, L., He, Y., & Zhou, D. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-0369-7_9
Self-citationAdvancing depression detection with role-playing LLMs and synthetic psychological interviews
Liu, Y., Hu, J., Chen, Y., & Zhang, Y. (2026) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-026-03337-5
Argumentative Multi-Agent Debate for Explainable Depression Detection in Clinical Interviews
Cao, H.-L., Pham, V., & Le, B. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.09.108
- Authors
- Zhang, L., Gao, Z., Zhou, D., & He, Y.
- Affiliations
- King's College London (GB)
- Southeast University (CN)
- Venue
- Findings of the Association for Computational Linguistics: ACL 2025
- Published
- 2025
- Pages
- 9927-9944
- OpenAlex
- W4412888563
- Cited by
- 9
- References
- 0
- Citations by year
- 2026: 6 · 2025: 3
- FWCI
- 17.19
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Findings of the Association for Computational Linguistics: ACL (Findings of ACL) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- Research Portal (King's College London) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- UK Research and Innovation (EP/V020579/1)
- Engineering and Physical Sciences Research Council (EP/V020579/1, EP/V020579/2)
- Topics
- Social Sciences › Psychology › Social Psychology › Mental Health via Writing
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Emotion and Mood Recognition
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Keywords
- depression detection, clinical interview, explainable AI, retrieval-augmented generation, hallucination mitigation, social intelligence, mental health screening
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
