RbtAct uses rebuttals to supervise training of models that generate actionable, perspective-specific review feedback, yielding gains in actionability over baselines on a new 75K dataset.
This includes missing or insufficient experiments, lack of ablation studies, weak baseline comparisons, unclear descriptions of datasets, or issues with hyperparameter selection
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
-
RbtAct: Rebuttal as Supervision for Actionable Review Feedback Generation
RbtAct uses rebuttals to supervise training of models that generate actionable, perspective-specific review feedback, yielding gains in actionability over baselines on a new 75K dataset.