A linear correction learned from 100 labeled examples per task substantially improves LLM-human agreement on evaluation tasks, including for smaller models.
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
-
Aligning Black-box Language Models with Human Judgments
A linear correction learned from 100 labeled examples per task substantially improves LLM-human agreement on evaluation tasks, including for smaller models.