Rethinking Loss Functions for Fact Verification

We explore loss functions for fact verification in the FEVER shared task.While the crossentropy 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 source code is available.