arXiv (All)
open access
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. Our findings demonstrate
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Expressive Vulnerabilities: Language and the Non-Human#747310
- Trust Me, I'm Your Developer: Self-Issued Authentication in Large Language Models#639617
- Pre-Prompt Identity Seeding: Assistant-First Self-Naming as a Partial, In-Context Mitigation Against Persona Manipulation#694206
- Leveraging Language Models for Log Statement Generation in Multilingual Scenarios: How Far Are We?#229584
- Assessing Suicide Risk in Arabic Crisis Helpline Calls: A Comparison of Arabic and English Large Language Models#819656
Record · ID 1355797
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive