LC-ICL improves few-shot NER and RE by using label-guided contrastive demonstrations that pair positive samples with error-annotated negative samples.
Thinking about GPT-3 in-context learning for biomedical ie? think again,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 3years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
unclear 1representative citing papers
Many-shot ICL with LLMs matches or exceeds supervised BERT on NER and generates high-quality labels for low-resource settings, producing ~10% absolute F1 gains when used to fine-tune BERT.
Decomposing annotation tasks using centers from centering theory reduces aggregate inferential load via a degrees-of-freedom model and enables better sub-task allocation.
citing papers explorer
-
Task Decomposition for Efficient Annotation
Decomposing annotation tasks using centers from centering theory reduces aggregate inferential load via a degrees-of-freedom model and enables better sub-task allocation.