Rethinking Loss Functions for Fact Verification
This work addresses fact verification for researchers and practitioners, but it is incremental as it focuses on optimizing loss functions for a specific dataset.
The paper tackled the problem of fact verification in the FEVER shared task by developing two task-specific loss functions that outperform the standard cross-entropy loss, with further improvements achieved through class weighting to address data imbalance.
We explore loss functions for fact verification in the FEVER shared task. While the cross-entropy loss is a standard objective for training verdict predictors, it fails to capture the heterogeneity among the FEVER verdict classes. In this paper, we develop two task-specific objectives tailored to FEVER. Experimental results confirm that the proposed objective functions outperform the standard cross-entropy. Performance is further improved when these objectives are combined with simple class weighting, which effectively overcomes the imbalance in the training data. The souce code is available at https://github.com/yuta-mukobara/RLF-KGAT