BetaEdit improves sequential editing of LLMs by addressing leakage in null-space methods through controlled updates and history-aware integration, outperforming prior approaches on large-scale edit sequences.
Can we edit factual knowledge by in-context learning? In Proceedings of the 2023 Conference on Empirical Meth- ods in Natural Language Processing, pages 4862–4876
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
BetaEdit: Null-Space Constrained Sequential Model Editing
BetaEdit improves sequential editing of LLMs by addressing leakage in null-space methods through controlled updates and history-aware integration, outperforming prior approaches on large-scale edit sequences.