Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{202360,
        author = {Jeet Prabhakar Naik and Nishad Bankar and Upendra Naik and Shruti Parsewar and Lisha Khairnar and Mahesh Nigade},
        title = {Misinformation Detection Using Large Language Model & APIs},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {7055-7057},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=202360},
        abstract = {Fake information on the internet spreads quite fast [1], and it’s getting tougher to handle. A message is endlessly shared, and long before people even bother to check it out, they already take it at face value. As a result, there is a need for tools that can help quickly and reliably check such claims. The website that we built for that purpose is discussed in this paper. It uses LLaMA, a large language model (LLM), Tavily API, and Jina API, which help in web search. Google’s Fact Check Tools API is also used to check if the claim has already been verified or not. After the user enters a claim, a result is shown along with an explanation showing it is true, false, or uncertain. The system was tested on 120 different types of claims, and the results show us how accurately the system detects misinformation after integrating APIs, and not just relying on LLaMa. The LLaMA model alone achieves an accuracy rate of only 34.2%, as it is not trained on the latest data. However, using all APIs resulted in 100% accuracy.},
        keywords = {misinformation detection, large language model, LLaMA, fact-checking, Jina AI, Tavily, Google Fact Check API, natural language processing},
        month = {May},
        }