In this paper, we explore the challenges associated with establishing an end-to-end fact-checking pipeline in a real-world context, covering over 90 languages. Our real-world experimental benchmarks demonstrate that fine-tuning Transformer models specifically for fact-checking tasks, such as claim detection and veracity prediction, provide superior performance over large language models (LLMs) like GPT-4, GPT-3.5-Turbo, and Mistral-7b. However, we illustrate that LLMs excel in generative tasks such as question decomposition for evidence retrieval. Through extensive evaluation, we show the efficacy of fine-tuned models for fact-checking in a multilingual setting and complex claims that include numerical quantities.
@article{arxiv.2402.12147,
title = {Surprising Efficacy of Fine-Tuned Transformers for Fact-Checking over Larger Language Models},
author = {Vinay Setty},
journal= {arXiv preprint arXiv:2402.12147},
year = {2024}
}