# Rethinking Loss Functions for Fact Verification

arXiv: https://arxiv.org/abs/2403.08174 · HTML: https://mlsanity.com/paper/2403.08174/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 28 references that are in the map.
- First posted on arXiv 13 Mar 2024.

## Builds on (most cited first, 14 of 14)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information](https://mlsanity.com/paper/2106.05707/) (2021)
- [Fine-grained Fact Verification with Kernel Graph Attention Network](https://mlsanity.com/paper/1910.09796/) (2019)
- [GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification](https://mlsanity.com/paper/1908.01843/) (2019)
- [Learning with Biased Complementary Labels](https://mlsanity.com/paper/1711.09535/) (2017)
- [Learning from Complementary Labels](https://mlsanity.com/paper/1705.07541/) (2017)
- [Complementary-Label Learning for Arbitrary Losses and Models](https://mlsanity.com/paper/1810.04327/) (2018)
- [ProoFVer: Natural Logic Theorem Proving for Fact Verification](https://mlsanity.com/paper/2108.11357/) (2021)
- [BEVERS: A General, Simple, and Performant Framework for Automatic Fact Verification](https://mlsanity.com/paper/2303.16974/) (2023)

## Abstract (arXiv)

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