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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Anik, Anirban Saha, Chowdhury, Md Fahimul Kabir, Wyckoff, Andrew, Choudhury, Sagnik Ray
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909787184168960
author Anik, Anirban Saha
Chowdhury, Md Fahimul Kabir
Wyckoff, Andrew
Choudhury, Sagnik Ray
author_facet Anik, Anirban Saha
Chowdhury, Md Fahimul Kabir
Wyckoff, Andrew
Choudhury, Sagnik Ray
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_11492
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ClaimIQ at CheckThat! 2025: Comparing Prompted and Fine-Tuned Language Models for Verifying Numerical Claims
Anik, Anirban Saha
Chowdhury, Md Fahimul Kabir
Wyckoff, Andrew
Choudhury, Sagnik Ray
Computation and Language
Artificial Intelligence
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.
title ClaimIQ at CheckThat! 2025: Comparing Prompted and Fine-Tuned Language Models for Verifying Numerical Claims
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2509.11492