A BERT model fine-tuned with ranking losses against BARTScore substitutes words to improve that score, outperforming supervised and LLM baselines on BARTScore-based metrics without human labels.
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
-
Learning to Substitute Words with Model-based Score Ranking
A BERT model fine-tuned with ranking losses against BARTScore substitutes words to improve that score, outperforming supervised and LLM baselines on BARTScore-based metrics without human labels.