REALM learns per-annotator expertise scalars unsupervised by modeling each label as an expertise-weighted mixture of the model's prediction and a uniform random guess, delivering up to 50% accuracy gains over naive noisy supervised fine-tuning on question-answering benchmarks.
Imitation learn- ing by estimating expertise of demonstrators,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
REALM: Reliable Expertise-Aware Language Model Fine-Tuning from Noisy Annotations
REALM learns per-annotator expertise scalars unsupervised by modeling each label as an expertise-weighted mixture of the model's prediction and a uniform random guess, delivering up to 50% accuracy gains over naive noisy supervised fine-tuning on question-answering benchmarks.