Metraipolis › archive › dc_14816f5365ea

When Retrieval Helps: Selective Retrieval for Single-Turn Mental-Health QA — arXiv:2609.03454

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03454
License (as archived)
CC0-1.0
Archived
2026-10-17T01:40:32.128Z
SHA-256 of the archived text
63f9927f04284f2e5ee696158be6bb5ddac527b62a120d4ce613990b105b121c
Stable URL of this page
https://metraipolis.com/documento/dc_14816f5365ea

How to cite

When Retrieval Helps: Selective Retrieval for Single-Turn Mental-Health QA — arXiv:2609.03454 — arXiv (en), https://arxiv.org/abs/2609.03454 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_14816f5365ea (Metraipolis archive dc_14816f5365ea, sha256 63f9927f04284f2e5ee696158be6bb5ddac527b62a120d4ce613990b105b121c)
BibTeX
@misc{dc14816f5365ea,
  title = {When Retrieval Helps: Selective Retrieval for Single-Turn Mental-Health QA — arXiv:2609.03454},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03454},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_14816f5365ea; sha256 63f9927f04284f2e5ee696158be6bb5ddac527b62a120d4ce613990b105b121c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03454. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.03454 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T01:11:43.535Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).