SaM selects and merges a few domain-expert LoRA models at inference time, outperforming a unified NER model by about 10% F1 on CrossNER and MIT.
Title resolution pending
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
-
Selecting and Merging: Towards Adaptable and Scalable Named Entity Recognition with Large Language Models
SaM selects and merges a few domain-expert LoRA models at inference time, outperforming a unified NER model by about 10% F1 on CrossNER and MIT.