REALM jointly learns model parameters and per-annotator expertise scalars during fine-tuning by modeling observed labels as mixtures of model predictions and uniform noise, improving accuracy under simulated annotation noise.
Fine-tuning pre-trained language model with weak supervision: A contrastive-regularized self-training approach
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
No citing papers match the current filters.