Retrieval-Augmented Generation in LLMs for Mental Health: Quantifying the Incremental Contribution of Retrieval Within a Layered Safety Architecture

• URL: http://arxiv.org/abs/2607.24817v1
• Date: Fri, 17 Jul 2026 06:32:12 GMT
• Title: Retrieval-Augmented Generation in LLMs for Mental Health: Quantifying the Incremental Contribution of Retrieval Within a Layered Safety Architecture
• Abstract summary: Digital mental health interventions (DMHIs) offer scalable support, but ensuring they accurately detect users' intent during volatile situations can be challenging.<n>This paper evaluates six Large Language models within a DMHI called Wysa, via a controlled comparison of RAG-enabled versus RAG-disabled modes.<n>The study computed classification accuracy, recall, precision and F1 scores against ground truth labels and tested differences for statistical significance.
• Score: 1.9213555198905314
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Digital mental health interventions (DMHIs) offer scalable support, but ensuring they accurately detect users' intent during volatile situations can be challenging. Pure parametric Large Language models (LLMs) do not contain specific safety critical architecture, and can miss critical cues, or hallucinate, undermining reliability. Retrieval Augmented Generation (RAG), which supplements an LLM with retrieved context, could enhance intent detection during volatile situations. Commercially available DMHIs typically combine multiple independent safety layers like rule-based filters, symbolic escalation protocols, and neural classification. The incremental contribution of any single layer, however, remains unquantified. This paper evaluates six LLM models within a DMHI called Wysa, via a controlled comparison of RAG-enabled versus RAG-disabled modes. Anonymized real and synthetic user-chatbot exchanges were annotated by a qualified clinical team against multi-class intent categories (e.g. self-harm, abuse, panic). The study computed classification accuracy, recall, precision and F1 scores against ground truth labels and tested differences for statistical significance. Performance was also examined by risk category and inter-model agreement. While RAG caused a rise in false alarms, the trade-off is consistent with safety-critical design principles that prioritize sensitivity, where flagged cases are routed to additional review rather than acted on directly. Overall, these findings support RAG as a promising approach to improve the accuracy, consistency and safety of LLM-driven DMHIs. Keywords: Digital Mental Health Intervention, Large Language Model, Retrieval Augmented Generation, Accuracy, Recall, Precision

Related papers

• Same Patient, Different Words, Different Diagnosis? Evaluating Semantic Stability in Clinical LLMs [5.580559622582594]
  We introduce three metrics to quantify model sensitivity: MeaningPreserving Variation Sensitivity (MVS), confidence variation (C), and Worst-Case Instability (WCI)<n>Our results demonstrate that differences between domain-specific (DS) models are mixed and highly model-dependent, i.e., domain specialization does not consistently improve or reduce robustness to meaning-preserving prompt reformulations.
  arXiv  Detail & Related papers  (2026-05-28T23:03:43Z)
• Green Shielding: A User-Centric Approach Towards Trustworthy AI [19.485991712624095]
  Green Shielding is a user-centric agenda for building evidence-backed deployment guidance.<n>We instantiate Green Shielding in medical diagnosis through HealthCareMagic-Diagnosis.<n>Although instantiated here in medical diagnosis, the agenda extends naturally to other decision-support settings and agentic AI systems.
  arXiv  Detail & Related papers  (2026-04-27T17:04:17Z)
• DeepSeek Robustness Against Semantic-Character Dual-Space Mutated Prompt Injection [45.67420390185547]
  We propose PromptFuzz-SC, a semantic-character dual-space mutation framework for evaluating robustness against prompt injection.<n>A hybrid search strategy combining epsilon-greedy exploration and hill-climbing refinement is adopted to efficiently discover high-quality adversarial prompts.<n> Experimental results on DeepSeek demonstrate that dual-space mutation achieves the strongest overall attack performance.
  arXiv  Detail & Related papers  (2026-04-14T10:20:15Z)
• MHDash: An Online Platform for Benchmarking Mental Health-Aware AI Assistants [2.89303424493]
  We present MHDash, an open-source platform designed to support the development, evaluation, and auditing of AI systems for mental health applications.<n>Our results reveal several key findings, including that simple baselines and advanced LLM APIs exhibit comparable overall accuracy yet diverge significantly on high-risk cases.<n>By releasing MHDash as an open platform, we aim to promote reproducible research, transparent evaluation, and safety-aligned development of AI systems for mental health support.
  arXiv  Detail & Related papers  (2026-01-30T22:03:31Z)
• Health-ORSC-Bench: A Benchmark for Measuring Over-Refusal and Safety Completion in Health Context [82.32380418146656]
  Health-ORSC-Bench is the first large-scale benchmark designed to measure textbfOver-Refusal and textbfSafe Completion quality in healthcare.<n>Our framework uses an automated pipeline with human validation to test models at varying levels of intent ambiguity.<n>Health-ORSC-Bench provides a rigorous standard for calibrating the next generation of medical AI assistants.
  arXiv  Detail & Related papers  (2026-01-25T01:28:52Z)
• Biosecurity-Aware AI: Agentic Risk Auditing of Soft Prompt Attacks on ESM-Based Variant Predictors [4.781986758380065]
  We introduce the Secure Agentic Genomic Evaluator (SAGE), an agentic framework for auditing the adversarial vulnerabilities of GFMs.<n>Using SAGE, we find that even state-of-the-art GFMs like ESM2 are sensitive to targeted soft prompt attacks.
  arXiv  Detail & Related papers  (2025-12-19T00:51:11Z)
• A Granular Study of Safety Pretraining under Model Abliteration [64.24346997570275]
  We study model abliteration, a lightweight projection technique designed to remove refusal-sensitive directions.<n>We issue 100 prompts with balanced harmful and harmless cases, classify responses as **Refusal** or **Non-Refusal** using multiple judges, and validate judge fidelity.<n>Our study produces a checkpoint-level characterization of which data-centric safety components remain robust under abliteration.
  arXiv  Detail & Related papers  (2025-10-03T07:01:45Z)
• Uncovering Overconfident Failures in CXR Models via Augmentation-Sensitivity Risk Scoring [1.9837702647603577]
  We propose an augmentation-sensitivity risk scoring (ASRS) framework to identify error-prone chest radiograph (CXR) cases.<n>ASRS scores stratify samples into stability quartiles, where highly sensitive cases show substantially lower recall.<n>ASRS provides a label-free means for selective prediction and clinician review, improving fairness and safety in medical AI.
  arXiv  Detail & Related papers  (2025-10-02T05:15:40Z)
• Beyond Benchmarks: Dynamic, Automatic And Systematic Red-Teaming Agents For Trustworthy Medical Language Models [87.66870367661342]
  Large language models (LLMs) are used in AI applications in healthcare.<n>Red-teaming framework that continuously stress-test LLMs can reveal significant weaknesses in four safety-critical domains.<n>A suite of adversarial agents is applied to autonomously mutate test cases, identify/evolve unsafe-triggering strategies, and evaluate responses.<n>Our framework delivers an evolvable, scalable, and reliable safeguard for the next generation of medical AI.
  arXiv  Detail & Related papers  (2025-07-30T08:44:22Z)
• Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs [54.90315421117162]
  We propose a novel poisoning method via completely harmless data.<n>Inspired by the causal reasoning in auto-regressive LLMs, we aim to establish robust associations between triggers and an affirmative response prefix.<n>We observe an interesting resistance phenomenon where the LLM initially appears to agree but subsequently refuses to answer.
  arXiv  Detail & Related papers  (2025-05-23T08:13:59Z)
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization [58.390885294401066]
  Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>We propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA)<n>We introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)
• MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks [104.50239783909063]
  Multimodal large language models with Retrieval Augmented Generation (RAG) have significantly advanced tasks such as multimodal question answering.<n>This reliance on external knowledge poses a critical yet underexplored safety risk: knowledge poisoning attacks.<n>We propose MM-PoisonRAG, the first framework to systematically design knowledge poisoning in multimodal RAG.
  arXiv  Detail & Related papers  (2025-02-25T04:23:59Z)

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.