Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse

ArXi:2601.11042v2 Announce Type: replace-cross Sequential knowledge editing in large language models often causes catastrophic collapse of the model's general abilities, especially for parameter-modifying methods. Existing approaches mitigate this issue through heuristic constraints on parameter updates, yet the mechanisms underlying such degradation remain insufficiently understood. In this work, we present a spectral analysis of sequential knowledge editing and show that a model's general abilities are closely associated with dominant singular directions of pretrained weight matrices.