Tool Mediation Alters Refusal Mechanisms in Large Language Models
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/meta-llama/llama-models
Sources
- Mind the GAP: Text Safety Does Not Transfer to Tool-Call Safety in LLM Agents
- Gemma 4 Technical Report
- There Is More to Refusal in Large Language Models than a Single Direction
- Ministral 3
- The Hydra Effect: Emergent Self-repair in Language Model Computations
- gpt-oss-120b & gpt-oss-20b Model Card
- Qwen3 Technical Report
- Qwen3Guard Technical Report
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems