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

Ronit Singhal, Pransh Patwa, Parth Patwa, Aman Chadha, Amitava Das
8/22/2024
cs.CLcs.AI

Official code: ronit-singhal/evidence-backed-fact-checking-using-rag-and-few-shot-in-context-learning-with-llms (7 stars, last commit 2024-10-04).

Abstract

Given the widespread dissemination of misinformation on social media, implementing fact-checking mechanisms for online claims is essential. Manually verifying every claim is very 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 (Schlichtkrull et al., 2023) to assess the performance of our fact-checking system. 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. Our Code is publicly available on https://github.com/ronit-singhal/evidence-backed-fact-checking-using-rag-and-few-shot-in-context-learning-with-llms.

View on arXivView PDF

Code Implementations(1)

ronit-singhal/evidence-backed-fact-checking-using-rag-and-few-shot-in-context-learning-with-llmsOfficial100%

Official Repository of the paper Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMs

70Jupyter NotebookAug 15, 20242 years ago

Similar Papers

Towards Automated Fact-Checking of Real-World Claims: Exploring Task Formulation and Assessment with LLMs

88% match2025

ClaimCheck: Real-Time Fact-Checking with Small Language Models

87% match2025

Fact-checking AI-generated news reports: Can LLMs catch their own lies?

87% match2025

FACT-GPT: Fact-Checking Augmentation via Claim Matching with LLMs

86% match2 repos72.8k2024

InFi-Check: Interpretable and Fine-Grained Fact-Checking of LLMs

85% match1 repo122026

HerO at AVeriTeC: The Herd of Open Large Language Models for Verifying Real-World Claims

85% match1 repo142024

Cite this paper

@article{singhal2024evidencebacked,
  title  = {Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMs},
  author = {Ronit Singhal and Pransh Patwa and Parth Patwa and Aman Chadha and Amitava Das},
  year   = {2024},
  eprint = {2408.12060},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2408.12060v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2408.12060.svg)](https://codeofpaper.com/paper/2408.12060)

Discussion