PRISM: Transfer and Limits of Activation Interventions in Tool-Calling Language Models
arXiv:2610.20808v1 Announce Type: new Abstract: 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,…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-10-16 04:00 · arXiv cs.CL
PRISM: Transfer and Limits of Activation Interventions in Tool-Calling Language Models