[Paper] PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models
Source: arXiv - 2606.09697v1
Overview
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 8019 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.
Key Contributions
This paper presents research in the following areas:
- cs.CL
Methodology
Please refer to the full paper for detailed methodology.
Practical Implications
This research contributes to the advancement of cs.CL.
Authors
- Gianluca Barmina
- Federico Torrielli
- Sven Harms
- Jacob Nielsen
- Felix Mächtle
- Stine Lyngsø Beltoft
- Peter Schneider-Kamp
- Thomas Eisenbarth
- Lukas Galke Poech
- Anne Lauscher
Paper Information
- arXiv ID: 2606.09697v1
- Categories: cs.CL
- Published: June 8, 2026
- PDF: Download PDF