conftrace_

refusal mechanism

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) safety alignment (2) reliable generation (1) knowledge scope (1) llm reliability (1) over refusal (1) internal state (1) activation pattern (1) activation steering (1) personally identifiable information (1)

Papers

Defeating Cerberus: Privacy-Leakage Mitigation in Vision Language Models EACL 2026 Differentiated Directional Intervention: A Framework for Evading LLM Safety Alignment AAAI 2026 Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning ICML 2025 Learn to Refuse: Making Large Language Models More Controllable and Reliable through Knowledge Scope Limitation and Refusal Mechanism EMNLP 2024