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
@article{arxiv.2403.08174,
title = {Rethinking Loss Functions for Fact Verification},
author = {Yuta Mukobara and Yutaro Shigeto and Masashi Shimbo},
journal= {arXiv preprint arXiv:2403.08174},
year = {2024}
}
Comments
Accepted to EACL 2024 (short paper). The souce code is available at https://github.com/yuta-mukobara/RLF-KGAT