Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models

arXiv:2305.14623v2 Announce Type: replace
Abstract: Fact-checking is an essential task in NLP that is commonly utilized for validating the factual accuracy of claims. Prior work has mainly focused on fine-tuning pre-trained languages models on specific datasets, which can be computationally intensive and time-consuming. With the rapid development of large language models (LLMs), such as ChatGPT and GPT-3, researchers are now exploring their in-context learning capabilities for a wide range of tasks. In this paper, we aim to assess the capacity …

abstract accuracy arxiv cs.cl datasets development fact-checking fine-tuning language language models languages large language large language models modules nlp prior type work