arXiv · 2611.14910
MuEdit: An efficient multi-task editing method towards inter-domain knowledge conflicts
Abstract
Large language models (LLMs) require frequent knowledge updates across heterogeneous domains, but existing editing methods fail when applied sequentially to multi-task settings. We trace this collapse to inter-domain null-space misalignment: heterogeneous tasks induce distinct Jacobian geometries, causing their common null space to shrink dramatically and leaving insufficient admissible directions for conflict-free updates. We propose the Conflict Index to quantify this geometric interference, and introduce Mu-Edit, which mitigates multi-task conflicts via (1) conflict-aware ordering to minimize cumulative interference, and (2) dynamic low-rank approximation to expand the null space when ordering alone is insufficient. Experiments across five functional domains and three backbones show that Mu-Edit significantly outperforms existing baselines in multi-task editing performance while preserving general capabilities, and remains effective under incremental task arrival.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Songshi Liang, Ting-En Lin, Zixuan Huang, Yuchuan Wu, Yongbin Li, Zihe Wang, Rui Yan. 2026-11-11. MuEdit: An efficient multi-task editing method towards inter-domain knowledge conflicts. https://searcharxiv.com/abs/2611.14910
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.