PRISM: Transfer and Limits of Activation Interventions in Tool-Calling Language Models

Overview

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, languages, and scales. Our findings demonstrate that leveraging lower-resource settings (specifically quantized NF4 labels and cross-lingual transfer) offers a robust pathway to expose and improve mod

SpinGraph analysis pending — check back after processing.