检索何时有益：面向单轮心理健康问答的选择性检索
When Retrieval Helps: Selective Retrieval for Single-Turn Mental-Health QA
浏览论文内容
中文总结 AI 辅助
本研究针对单轮心理健康问答，提出选择性检索策略，在CounselBench系列基准实验中验证其可平衡检索的针对性提升与安全风险，优于闭卷及始终检索设置。
中文摘要 AI 辅助
检索增强生成（RAG）可提升大语言模型回答的针对性与依据性，但在单轮心理健康问答中其效果并非始终有益，用户查询常结合情绪困扰、治疗顾虑及安全敏感需求。本研究探讨检索在心理健康问答中何时有益或有害，以及轻量型选择性检索策略能否更好控制该权衡。我们基于三个草稿条件效用维度（心理教育需求、应对需求、回答针对性）及基于规则的安全触发来衡量检索需求。借鉴基于心理治疗的RAG系统coTherapist，我们构建包含应对策略、心理教育及安全资源的紧凑可控指南语料库。我们使用QLoRA在MentalChat16K上微调指令调优生成器，并在CounselBench-Eval和CounselBench-Adv上对比闭卷、始终检索、选择性检索设置。实验表明，检索在该领域并非始终有益：始终检索提升针对性但降低整体质量并引入额外安全敏感失败；选择性检索在低需求案例中保留闭卷行为，同时避免无条件检索导致的额外性能下降，支持检索激活是安全敏感控制决策的观点。
英文摘要
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.
发表机构
- Korea Institute of Energy Technology（韩国能源技术研究院）
机构由 AI 辅助整理，请以论文原文为准。
