This paper introduces PsychoSafe, a refusal framework grounded in evidence-based intervention strategies, and evaluates prompting and fine-tuning approaches for psychologically informed LLM refusals.
This paper evaluates six confidence-estimation methods for activation oracles and finds that bootstrap mode frequency is the best-calibrated method among those tested, while log-probability can serve as a cheaper triage signal.
This study introduces the Author-Reviewer-Organizer (ARO) framework and presents a large-scale empirical assessment of indirect prompt injection in AI-assisted peer review, finding that hidden instructions are followed in 78% of cases for ChatGPT and 86% for Gemini.
A 20-hour course on prompt engineering methodologies and critical thinking about prompts, taught at the Master in Ethics and Artificial Intelligence, University of Torino.
This paper introduces BLACK, a novel methodology for prompting large language models and generative AI systems.