arxiv:2408.12060

Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMs

Published on Aug 22

· Submitted by

amanchadha on Aug 23

Upvote

Authors:

Aman Chadha ,

Abstract

Given the widespread dissemination of misinformation on social media, implementing fact-checking mechanisms for online claims is essential. Manually verifying every claim is highly challenging, underscoring the need for an automated fact-checking system. This paper presents our system designed to address this issue. We utilize the Averitec dataset to assess the veracity of claims. In addition to veracity prediction, our system provides supporting evidence, which is extracted from the dataset. We develop a Retrieve and Generate (RAG) pipeline to extract relevant evidence sentences from a knowledge base, which are then inputted along with the claim into a large language model (LLM) for classification. We also evaluate the few-shot In-Context Learning (ICL) capabilities of multiple LLMs. Our system achieves an 'Averitec' score of 0.33, which is a 22% absolute improvement over the baseline. All code will be made available on All code will be made available on https://github.com/ronit-singhal/evidence-backed-fact-checking-using-rag-and-few-shot-in-context-learning-with-llms.

View arXiv page View PDF Add to collection

Community

amanchadha

Paper author Paper submitter Aug 23

•

edited Aug 23

We present an evidence-backed automated fact-checking system using Retrieval-Augmented Generation (RAG) and few-shot In-Context Learning (ICL) with Large Language Models (LLMs).

Methodology: We develop a RAG pipeline to extract relevant evidence, combined with ICL for veracity prediction
Minimal Training: We require only a few training samples, eliminating the need for large annotated datasets
Performance: We achieve state-of-the-art results on the Averitec dataset, outperforming the baseline by a significant margin