PRISM2 min read
PRISM: Transfer and Limits of Activation Interventions in Tool-Calling Language Models
Recent literature shows that unsafe tool calls can often accompany textual refusals in language models. To investigate this hidden vulnerability, we introduce PRISM, a framework for evaluating the transfer of activation interventions across precision, languages, and scales.
By Giovana Kerche Bon\'as, Thales Sales Almeida, Marcelo da Silva Reis, Rodrigo Nogueira, Marcos Meideiros RaimundoarXiv - cs.CL (NLP)
Read the full story
Originally published by arXiv - cs.CL (NLP) on Oct 16, 2026.
Comments
Sign in to join the discussion.