Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms Paper • 2505.20322 • Published May 23, 2025 • 14
CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners Paper • 2503.16356 • Published Mar 20, 2025 • 15
How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training Paper • 2502.11196 • Published Feb 16, 2025 • 23
ReLearn: Unlearning via Learning for Large Language Models Paper • 2502.11190 • Published Feb 16, 2025 • 30
Knowledge Mechanisms in Large Language Models: A Survey and Perspective Paper • 2407.15017 • Published Jul 22, 2024 • 34