作者位次 #3/4ACL 2026Findings· Findings of ACL
One Mask to Rule Them All: On Hidden Facts after Editing and How to Find Them
Ali Holmov · Paul Youssef · Nandi Schoots · Christin Seifert
摘要
Knowledge editing methods such as ROME and MEMIT update factual associations in transformer models by modifying MLP weights. While evaluated mainly by output behavior, their internal mechanism remains underexplored. We investigate whether edits rely on a common mechanism, regardless of which fact...