English

Rethinking Loss Functions for Fact Verification

Computation and Language 2024-03-14 v1 Artificial Intelligence

Abstract

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

Keywords

Cite

@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

R2 v1 2026-06-28T15:18:08.361Z