Paper Detail
Gianluca Barmina, Federico Torrielli, Sven Harms, Jacob Nielsen, Felix Mächtle, Stine Lyngsø Beltoft, Peter Schneider-Kamp, Thomas Eisenbarth, Lukas Galke Poech, Anne Lauscher
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.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{barmina2026psychosafe,
title = {PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models},
author = {Gianluca Barmina and Federico Torrielli and Sven Harms and Jacob Nielsen and Felix Mächtle and Stine Lyngsø Beltoft and Peter Schneider-Kamp and Thomas Eisenbarth and Lukas Galke Poech and Anne Lauscher},
year = {2026},
abstract = {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 commu},
url = {https://arxiv.org/abs/2606.09697},
keywords = {cs.CL, large language models, refusal framework, psychological grounding, prompting, parameter-efficient fine-tuning, Qwen 3.5 27B, LLM judge, SORRY-Bench, XSTest, code available, huggingface daily},
eprint = {2606.09697},
archiveprefix = {arXiv},
}
{}