Team06 - Fake News Detection Using Large Language Models with Retrieval-Augmented Generation (RAG)

Indian Institute of Science Summer 2025 DA225o Submission4 Authors

Keywords: Fake news detection, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), Prompt Engineering, Langchain

TL;DR: This project aims to develop an AI-powered fake news detection prototype using Large Language Models and Retrieval-Augmented Generation, starting with English and potentially expanding to Indian languages.

Abstract:

In today’s digital era, where information is accessible instantly and news is disseminated across numerous platforms, distinguishing real news from fake has become critically important. The proliferation of misinformation can significantly influence public opinion, disrupt social harmony, and serve as a tool for personal or political gain. Consequently, developing systems to automatically detect and filter fake news has become a pressing technological and societal challenge.

This project aims to build a prototype system for fake news detection by leveraging Large Language Models (LLMs) in conjunction with a Retrieval-Augmented Generation (RAG) framework. The goal is to utilize advanced AI techniques to identify patterns, linguistic cues, and contextual inconsistencies that are indicative of false or misleading information.

Submission Number: 4