<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Psychological Safety on Federico Torrielli</title><link>https://federicotorrielli.github.io/tags/psychological-safety/</link><description>Recent content in Psychological Safety on Federico Torrielli</description><generator>Hugo -- 0.152.2</generator><language>en</language><lastBuildDate>Mon, 08 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://federicotorrielli.github.io/tags/psychological-safety/index.xml" rel="self" type="application/rss+xml"/><item><title>PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models</title><link>https://federicotorrielli.github.io/papers/psychosafe/</link><pubDate>Mon, 08 Jun 2026 00:00:00 +0000</pubDate><guid>https://federicotorrielli.github.io/papers/psychosafe/</guid><description>A psychologically informed refusal framework for large language models, evaluated with prompting and fine-tuning on high-risk request domains. Preprint on arXiv.</description></item></channel></rss>