mlsanityData to 14 Oct 2026

When Retrieval Helps: Selective Retrieval for Single-Turn Mental-Health QA

arXiv 2609.03454 ↗First posted 3 Sep 2026cs.CL cs.IRcited by 0

On the map: Retrieval-augmented generation → Medical and biomedical RAG

Abstract (arXiv)

Retrieval-augmented generation (RAG) can improve the specificity and grounding of large language model responses, but its effect is not uniformly beneficial in single-turn mental-health question answering, where user queries often combine emotional distress, treatment concerns, and safety-sensitive needs. We study when retrieval helps or hurts mental-health QA, and whether a lightweight selective retrieval policy can better control this trade-off. We operationalize retrieval need using three draft-conditioned utility dimensions: psychoeducational need, coping need, and response specificity, together with a rule-based safety trigger. Following psychotherapy-grounded RAG systems such as coTherapist, we construct a compact and controllable guideline corpus comprising coping-strategy, psychoeducational, and safety resources. We fine-tune an instruction-tuned generator on MentalChat16K using QLoRA and compare Closed-book, Always Retrieval, and Selective Retrieval settings on CounselBench-Eval and CounselBench-Adv. Experiments show that retrieval is not uniformly beneficial in this domain. Always Retrieval improves specificity but lowers overall quality and introduces additional safety-sensitive failures. Selective Retrieval preserves closed-book behavior for low-need cases while avoiding the additional degradation caused by unconditional retrieval, supporting the view that retrieval activation is a safety-sensitive control decision.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation. Builds on 16 of its 27 references that are in the map. First posted on arXiv 3 Sep 2026.

Builds on

16 of 27 references.

References · 16

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  4. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  6. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  7. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  8. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  9. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  10. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  11. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  12. 2024SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generationcited by 40
4 more
  1. 2025MentalChat16K: A Benchmark Dataset for Conversational Mental Health Assistancecited by 39
  2. 2024RAGGED: Towards Informed Design of Scalable and Stable RAG Systemscited by 24
  3. 2024CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Controlcited by 13
  4. 2026coTherapist: A Behavior-Aligned Small Language Model to Support Mental Healthcare Expertscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Mind the Gap: Aligning Knowledge Bases with User Needs to Enhance Mental Health Retrieval
  2. 2026Retrieval-Augmented Generation in LLMs for Mental Health: Quantifying the Incremental Contribution of Retrieval Within a Layered Safety Architecture
  3. 2026Reasoning Over Recall: Evaluating the Efficacy of Generalist Architectures vs. Specialized Fine-Tunes in RAG-Based Mental Health Dialogue Systems
  4. 2025OnRL-RAG: Real-Time Personalized Mental Health Dialogue System
  5. 2025A Systematic Evaluation of LLM Strategies for Mental Health Text Analysis: Fine-tuning vs. Prompt Engineering vs. RAG
  6. 2024Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QA
  7. 2026When Retrieval Doesn't Help: A Large-Scale Study of Biomedical RAG
  8. 2025Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain