Label-aware debiased causal reasoning for Natural Language Inference

Label-aware debiased causal reasoning for Natural Language Inference

Recently, researchers have argued that the impressive performance of Natural Language Inference (NLI) models is highly due to the spurious correlations existing in training data, which makes models vulnerable and poorly generalized. Some work has made preliminary debiased attempts by developing data...

Full description

Bibliographic Details
Main Authors: Kun Zhang, Dacao Zhang, Le Wu, Richang Hong, Ye Zhao, Meng Wang
Format: Article
Language:English
Published: KeAi Communications Co. Ltd. 2024-01-01
Series:AI Open
Subjects:
Natural language inference
Spurious correlations
Debiased reasoning
Causal effect
Online Access:http://www.sciencedirect.com/science/article/pii/S2666651024000081

Internet

http://www.sciencedirect.com/science/article/pii/S2666651024000081

Similar Items