End-to-end multilingual fact-checking at scale

arXiv:2402.12147v1 Announce Type: new
Abstract: In this article, we describe how you can perform end-to-end fact-checking in over 100 languages using Factiverse AI models. We also show through an experimental benchmark that fine-tuned models tailored for fact-checking tasks outperform Large Language Models such as GPT-4, GPT-3.5-Turbo, and Mistral-7b.

abstract ai models article arxiv benchmark cs.ai cs.cl experimental fact-checking gpt gpt-3 gpt-3.5 gpt-3.5-turbo gpt-4 language language models languages large language large language models mistral multilingual scale show tasks through turbo type