DTO is a new differentiable objective combining fidelity to reference rewrites and semantic consistency that outperforms MLE and preference baselines while matching LLMs on TimeTravel and ART datasets.
BERTTune: Fine-tuning neural machine translation with BERTScore,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DTO: a Differentiable Training Objective for Effective Counterfactual Story Rewriting
DTO is a new differentiable objective combining fidelity to reference rewrites and semantic consistency that outperforms MLE and preference baselines while matching LLMs on TimeTravel and ART datasets.