DS@GT at CheckThat! 2025: Evaluating Context and Tokenization Strategies for Numerical Fact Verification
This work addresses automated fact-checking of numerical claims, but it is incremental as it builds on existing datasets and methods without major breakthroughs.
The study tackled numerical fact verification by evaluating context windows and tokenization strategies, finding that neither right-to-left tokenization nor longer contexts improved performance, with the best system achieving a competitive macro-average F1 score of 0.57 and placing among the top submissions.
Numerical claims, statements involving quantities, comparisons, and temporal references, pose unique challenges for automated fact-checking systems. In this study, we evaluate modeling strategies for veracity prediction of such claims using the QuanTemp dataset and building our own evidence retrieval pipeline. We investigate three key factors: (1) the impact of more evidences with longer input context windows using ModernBERT, (2) the effect of right-to-left (R2L) tokenization, and (3) their combined influence on classification performance. Contrary to prior findings in arithmetic reasoning tasks, R2L tokenization does not boost natural language inference (NLI) of numerical tasks. A longer context window does also not enhance veracity performance either, highlighting evidence quality as the dominant bottleneck. Our best-performing system achieves competitive macro-average F1 score of 0.57 and places us among the Top-4 submissions in Task 3 of CheckThat! 2025. Our code is available at https://github.com/dsgt-arc/checkthat-2025-numerical.