Advancing Fake News Detection with Large Language Models via Chain-of-Thought Reasoning

DOI

10.2991/978-94-6463-858-5_21How to use a DOI?

Keywords

Fake News; LLMs; GPT; ClaimBuster; Chain of Thought (CoT); NLP

Abstract

This research introduces a novel framework for detecting fake news using advanced transformer models combined with Chain-of-Thought (CoT) reasoning. The study utilizes the GossipCop dataset, employing ALBERT, Distilled GPT-2, and Google Flan T5 for reasoning-based representations. ClaimBuster was used for verification, and an MLP classifier ranked embeddings, achieving 92% accuracy. The results highlight the potential of CoT-based reasoning in enhancing fake news detection.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Avighyat Srivastav
AU  - Shivani Tufchi
AU  - Aryan Singh Kaushik
AU  - Maahir Chugh
PY  - 2025
DA  - 2025/11/04
TI  - Advancing Fake News Detection with Large Language Models via Chain-of-Thought Reasoning
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 226
EP  - 244
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_21
DO  - 10.2991/978-94-6463-858-5_21
ID  - Srivastav2025
ER  -