PsychoSafe：在大语言模型中引发基于心理学的拒绝
PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models
AI总结：
提出PsychoSafe框架，将LLM的拒绝行为重构为基于证据干预策略的结构化支持性沟通，通过构建5个心理风险领域的8019个提示-响应对，对Qwen 3.5 27B进行提示和参数高效微调，在拒绝质量上比通用基线提升28.1%，同时保持非拒绝任务性能。
摘要：
大型语言模型（LLM）经常面临应被拒绝的请求，这造成了帮助性与伤害预防之间的权衡。然而，拒绝本身可能是有帮助的。在涉及危机、胁迫或意图升级的高风险交互中，生硬的不服从可能防止直接伤害，但仍未能支持请求背后的人的需求。我们提出了PsychoSafe，一个基于心理学的拒绝框架，将拒绝重构为基于证据干预策略的结构化支持性沟通。为了开发PsychoSafe，我们构建了一个包含8019个提示-响应对的语料库，涵盖五个心理上显著的风险领域，并对Qwen 3.5 27B应用提示和参数高效微调。在一个包含500个提示的平衡验证集上，通过LLM评判器评估并经人工评分验证，PsychoSafe提示在拒绝质量上比通用基线提高了28.1%，在外部资源转介（+46.8%）和心理基础（+34.8%）方面尤为突出，同时保持了非拒绝任务的下游性能。微调实现了近乎完美的拒绝和资源转介率，但降低了响应相关性。在SORRY-Bench和XSTest上的额外评估显示，域内鲁棒性强但域外泛化有限，这表明未来的工作应多样化微调数据，以帮助模型有选择地而非机械地应用干预措施。
英文摘要：
Large language models (LLMs) routinely face requests that should be refused, creating a trade-off between helpfulness and harm prevention. However, refusals themselves can be helpful. In high-risk interactions involving crisis, coercion, or escalating intent, blunt non-compliance may prevent direct harm while still failing to support the needs of the person behind the request. We present PsychoSafe, a psychologically-informed refusal framework that reframes refusal as structured supportive communication grounded in evidence-based intervention strategies. To develop PsychoSafe, we construct a corpus of 8,019 prompt-response pairs spanning five psychologically salient risk domains and apply prompting and parameter-efficient fine-tuning to Qwen 3.5 27B. On a balanced validation set of 500 prompts, evaluated with an LLM judge and validated through human ratings, PsychoSafe prompting improves overall refusal quality by 28.1% over a generic baseline, with particularly strong gains in external resource referral (+46.8%) and psychological grounding (+34.8%), while preserving downstream performance on non-refusal tasks. Fine-tuning achieves near-perfect refusal and resource-referral rates but reduces response relevance. Additional evaluations on SORRY-Bench and XSTest show strong in-domain robustness but limited out-of-domain generalization, suggesting that future work should diversify fine-tuning data to help models apply interventions selectively rather than schematically.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
