Transitive self-consistency evaluation of NLI models without gold labels
Authors:
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 22637-22653
Abstract
Wei Wu, Mark Last. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.Keywords
This publication has 5 references indexed in Scilit:
- Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference2025
- Consistency Analysis of ChatGPT2023
- SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in SummarizationTransactions of the Association for Computational Linguistics, 2022
- IMPLI: Investigating NLI Models’ Performance on Figurative Language2022
- Neural Network Acceptability JudgmentsTransactions of the Association for Computational Linguistics, 2019