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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Miaoran, Peng, Baolin, Galley, Michel, Gao, Jianfeng, Zhang, Zhu
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916184780177408
author Li, Miaoran
Peng, Baolin
Galley, Michel
Gao, Jianfeng
Zhang, Zhu
author_facet Li, Miaoran
Peng, Baolin
Galley, Michel
Gao, Jianfeng
Zhang, Zhu
contents 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 of LLMs for fact-checking by introducing Self-Checker, a framework comprising a set of plug-and-play modules that facilitate fact-checking by purely prompting LLMs in an almost zero-shot setting. This framework provides a fast and efficient way to construct fact-checking systems in low-resource environments. Empirical results demonstrate the potential of Self-Checker in utilizing LLMs for fact-checking. However, there is still significant room for improvement compared to SOTA fine-tuned models, which suggests that LLM adoption could be a promising approach for future fact-checking research.
format Preprint
id arxiv_https___arxiv_org_abs_2305_14623
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models
Li, Miaoran
Peng, Baolin
Galley, Michel
Gao, Jianfeng
Zhang, Zhu
Computation and Language
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 of LLMs for fact-checking by introducing Self-Checker, a framework comprising a set of plug-and-play modules that facilitate fact-checking by purely prompting LLMs in an almost zero-shot setting. This framework provides a fast and efficient way to construct fact-checking systems in low-resource environments. Empirical results demonstrate the potential of Self-Checker in utilizing LLMs for fact-checking. However, there is still significant room for improvement compared to SOTA fine-tuned models, which suggests that LLM adoption could be a promising approach for future fact-checking research.
title Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2305.14623