AI RESEARCH
Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs
arXiv CS.LG
•
ArXi:2506.13727v2 Announce Type: replace Large Language Models (LLMs) are widely deployed in real-world applications, yet their internal mechanisms remain difficult to interpret and control, limiting our ability to diagnose and correct undesirable behaviors. Mechanistic interpretability addresses this challenge by identifying circuits -- subsets of model components responsible for specific behaviors. However, discovering such circuits in LLMs remains difficult due to their scale and complexity.