Fine-tuning self-rationalization models on few examples transfers to 19 OOD NLI-related datasets nearly as well as full-data fine-tuning, and the Acceptability score is the best reference-free explanation metric tested.
In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5008–5020, Online
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
-
Self-Rationalization in the Wild: A Large Scale Out-of-Distribution Evaluation on NLI-related tasks
Fine-tuning self-rationalization models on few examples transfers to 19 OOD NLI-related datasets nearly as well as full-data fine-tuning, and the Acceptability score is the best reference-free explanation metric tested.