01 / MOTIVATION
Why this work matters
Numerical fact-checking calls for comparisons between prompts and targeted adaptation rather than assuming a general-purpose model is sufficient.
A comparison of prompted and fine-tuned language models for numerical claim verification.
02 / METHODOLOGY
Research approach
The paper compares prompted and fine-tuned language models for classifying numerical claims.
03 / CONTRIBUTIONS
Main contribution
Comparison of prompting and LoRA fine-tuning for numerical claim verification.
Consult the complete publication for numerical findings and experimental qualifications.
04 / PUBLICATION
Read the paper
Anirban Saha Anik, Md Fahimul Kabir Chowdhury, Andrew Wyckoff, and Sagnik Ray Choudhury. (2025). ClaimIQ at CheckThat! 2025: Comparing Prompted and Fine-Tuned Language Models for Verifying Numerical Claims. Working Notes of CLEF 2025, CEUR Workshop Proceedings, Vol. 4038, pp. 795–803.