SetKE couples bipartite matching with memory editing to update sets of overlapping knowledge triples in large language models, outperforming prior editors on the new EditSet benchmark.
Does large language model contain task-specific neurons? In Proceedings of the 2024 Conference on Empirical Methods in Natural Lan- guage Processing, pages 7101–7113,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SetKE: Knowledge Editing for Knowledge Elements Overlap
SetKE couples bipartite matching with memory editing to update sets of overlapping knowledge triples in large language models, outperforming prior editors on the new EditSet benchmark.