AINeutralarXiv – CS AI · 6h ago6/10
🧠
When Attribution Patching Lies: Diagnosis and a Second-Order Correction
Researchers have identified systematic errors in attribution patching, a widely-used gradient-based method for interpreting language model behavior, and developed a Hessian-vector-product correction that eliminates leading-order errors with minimal computational overhead. The work provides practical tools including reliability scores and error bounds, enabling more accurate circuit identification in mechanistic interpretability research across model scales from 124M to 9B parameters.