Date of Award

7-8-2024

Publication Type

Thesis

Degree Name

M.Sc.

Department

Computer Science

Keywords

Fake News Detection;Google Search API;Large Language Model;Retrieval-Augmented Generation;Sparse Mixture of Experts

Supervisor

Saeed Samet

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

The rapid spread of false information on social media has grown to be a serious problem that influences public opinion and decision-making. Fake news spreads rapidly and extensively, often outpacing efforts to debunk or mitigate its effects. Traditional methods for detecting fake news face numerous challenges, including the necessity for extensive model training and the potential for inherent biases. Although Large Language Models (LLMs) have seen substantial improvements recently, their use in fake news detection poses the risk of producing false or misleading information due to their possible hallucinations. This study presents a new strategy to combat fake news by integrating Mixtral 8x7B, a Sparse Mixture of Experts (SMoE) Large Language Model, with a Retrieval-Augmented Generation (RAG) framework. Our framework employs Google's search API to retrieve relevant articles in real time, harnessing Mixtral's sophisticated language processing capabilities and RAG's ability to access current information dynamically. Initial results are promising, indicating that our approach performs comparably to established fake news detection techniques. Our method operates without the need for extensive model training, offering significant cost savings and contributing to developing more efficient tools for detecting misinformation in the digital era, which will help stop the spread of misleading data more efficiently.

Available for download on Sunday, January 05, 2025

Share

COinS