Batching texts and stacking variables in LLM prompts reduces annotation costs by over 80% while maintaining accuracy within 2pp of single-item baselines for most models, with errors smaller than human inter-coder disagreement.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Researchers waste 80% of LLM annotation costs by classifying one text at a time
Batching texts and stacking variables in LLM prompts reduces annotation costs by over 80% while maintaining accuracy within 2pp of single-item baselines for most models, with errors smaller than human inter-coder disagreement.