Rethinking Loss Functions for Fact Verification
Not on the map. Why?
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
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 28 references that are in the map. First posted on arXiv 13 Mar 2024.
Builds on
14 of 28 references.
References · 14
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
- 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
- 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
- 2021Deep Long-Tailed Learning: A Surveycited by 416
- 2021FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured informationcited by 166
- 2019Fine-grained Fact Verification with Kernel Graph Attention Networkcited by 105
- 2019GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verificationcited by 100
- 2017Learning with Biased Complementary Labelscited by 93
- 2017Learning from Complementary Labelscited by 88
- 2018Complementary-Label Learning for Arbitrary Losses and Modelscited by 57
2 more
Built on by
Not cited yet.