arXiv:2610.20808v2 cs.CL

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

Giovana Kerche Bon\'as, Thales Sales Almeida, Marcelo da Silva Reis, Rodrigo Nogueira, Marcos Meideiros Raimundo

제출 2026-11-20

원문 초록

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 model alignment. Notably, using behavioral labels from an NF4 copy enables stable intervention estimation even with very few scenarios. Furthermore, these alignment improvements transfer effectively across languages: five-language NF4-supervised directions successfully transfer to held-out Arabic, reducing unsafe violations in Llama-3.1-8B by 21.95 percentage points without target-language tuning. By mapping paired benign activations, we also successfully transfer these safety interventions to much larger models (up to 70B parameters). Ultimately, PRISM highlights how auxiliary supervision from compressed models and multilingual data can uncover and mitigate hazardous tool-calling behaviors across different model families. We release all experimental code and supporting artifacts at https://github.com/GiKerche/prism, alongside an interactive explorer of recorded model responses and experimental results at https://gikerche.github.io/prism/.

제출 이력

확인된 버전만 표시합니다. 전체 제출 이력은 arXiv 원문에서 확인하세요.

  1. arXiv:2610.20808v2제출 시각 미확인

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

공통 태그로 연결된 공개 논문이 아직 없습니다.

토론

이 논문과 연결된 포럼 글이 아직 없습니다.