ClaimIQ at CheckThat! 2025: Comparing Prompted and Fine-Tuned Language Models for Verifying Numerical Claims
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 14 of its 25 references that are in the map. First posted on arXiv 15 Sep 2025.
Builds on
14 of 25 references.
References · 14
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
- 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
- 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 298
- 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documentscited by 257
- 2024Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systemscited by 87
- 2024A Survey on Retrieval-Augmented Text Generation for Large Language Modelscited by 77
- 2023Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvementscited by 42
- 2024Evidence-Driven Retrieval Augmented Response Generation for Online Misinformationcited by 32
- 2024Retrieval Augmented Fact Verification by Synthesizing Contrastive Argumentscited by 25
- 2024QuanTemp: A real-world open-domain benchmark for fact-checking numerical claimscited by 23
- 2025Zero-shot and Few-shot Learning with Instruction-following LLMs for Claim Matching in Automated Fact-checkingcited by 12
- 2024Face the Facts! Evaluating RAG-based Pipelines for Professional Fact-Checkingcited by 5
Built on by
Citing papers per year: 2026: 2.
2 papers.