pith. sign in

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 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

REALM: Reliable Expertise-Aware Language Model Fine-Tuning from Noisy Annotations

cs.LG · 2026-04-19 · unverdicted · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • REALM: Reliable Expertise-Aware Language Model Fine-Tuning from Noisy Annotations cs.LG · 2026-04-19 · unverdicted · none · ref 11

    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.