ClaimIQ at CheckThat! 2025: Comparing Prompted and Fine-Tuned Language Models for Verifying Numerical Claims

Abstract
This paper presents our system for Task 3 of the CLEF 2025 CheckThat! Lab, which focuses on verifying numerical and temporal claims using retrieved evidence. We explore two complementary approaches: zero-shot prompting with instruction-tuned large language models (LLMs) and supervised fine-tuning using parameter-efficient LoRA. To enhance evidence quality, we investigate several selection strategies, including full-document input and top-k sentence filtering using BM25 and MiniLM. Our best-performing model LLaMA fine-tuned with LoRA achieves strong performance on the English validation set. However, a notable drop in the test set highlights a generalization challenge. These findings underscore the importance of evidence granularity and model adaptation for robust numerical fact verification.

Keywords: Claim Verification, Numerical Claims, Large Language Models, Fact-Checking, Misinformation Detection

Resources

• 📄 Paper: CEUR-WS Vol-4038

BibTeX

@article{anik2025claimiq,
  title={ClaimIQ at CheckThat! 2025: comparing prompted and fine-tuned language models for verifying numerical claims},
  author={Anik, Anirban Saha and Chowdhury, Md Fahimul Kabir and Wyckoff, Andrew and Choudhury, Sagnik Ray},
  journal={arXiv preprint arXiv:2509.11492},
  year={2025}
}

Recommended citation: Anirban Saha Anik, Md Fahimul Kabir Chowdhury, Andrew Wyckoff, Sagnik Ray Choudhury. "ClaimIQ at CheckThat! 2025: Comparing Prompted and Fine-Tuned Language Models for Verifying Numerical Claims." Working Notes of the Conference and Labs of the Evaluation Forum (CLEF 2025).
Download Paper