LLMs Solution to Fake News, Disinformation, and Hoaxes: Llama 3 [70B]-based Hoax Detection and Counteraction System
DOI:
https://doi.org/10.56741/jnest.v4i02.952Keywords:
Large Language Models (LLMs), Llama 3, Hoax Detection, Disinformation, Fake News, Digital LiteracyAbstract
In the digital age, hoaxes or false information are a significant challenge, as they can harm public comprehension, form inaccurate opinions, and endanger the health and safety of individuals. Artificial intelligence technology, particularly large language models (LLMs) like Llama 3, provides an innovative solution to these challenges. A sophisticated generative model with superior natural language processing capabilities, Llama 3 enables the effective detection and clarification of hoaxes. A dataset that is seven times larger than its antecedent, Llama 2, is utilized to train this model. The dataset has a token capacity of up to 128K and a context length of up to 8 K. By utilizing these capabilities, Llama 3 is capable of comprehending context, offering responses that are grounded in scientific data, and reducing response errors. Educational chatbots, interactive web platforms, and mobile applications that are based on Llama 3 can be implemented. This model effectively identifies and clarifies false information regarding cosmic rays that are purportedly hazardous through the presentation of pertinent scientific facts, as demonstrated by case studies. Llama 3's capabilities encompass its capacity to modify parameters to generate valid and pertinent responses. This renders it a critical instrument for bolstering community resilience to the dissemination of falsehoods, as well as digital literacy and awareness. Llama 3, which is open source, facilitates global collaboration in the development of a more secure and trustworthy information ecosystem.
Downloads
References
M. B. R. Gus Rijal, A. Hisam, and A. Basit, ‘The Dangers of Hoaxes in Building Civil Society in the Era of the Industrial Revolution 4.0’, International Journal of Social Science and Religion (IJSSR), pp. 117–138, May 2021, doi: 10.53639/ijssr.v2i2.42. DOI: https://doi.org/10.53639/ijssr.v2i2.42
D. S. M and Hairunnisa, ‘The Phenomenon of Fake News (Hoax) in Mass Communication: Causes, Impacts, and Solutions’, Open Access Indonesia Journal of Social Sciences, vol. 6, no. 3, pp. 980–988, May 2023, doi: 10.37275/oaijss.v6i3.161. DOI: https://doi.org/10.37275/oaijss.v6i3.161
M. S. Treder, S. Lee, and K. A. Tsvetanov, ‘Introduction to Large Language Models (LLMs) for dementia care and research’, Frontiers in Dementia, vol. 3, May 2024, doi: 10.3389/frdem.2024.1385303. DOI: https://doi.org/10.3389/frdem.2024.1385303
M. A. K. Raiaan et al., ‘A Review on Large Language Models: Architectures, Applications, Taxonomies, Open Issues and Challenges’, IEEE Access, vol. 12, pp. 26839–26874, 2024, doi: 10.1109/ACCESS.2024.3365742. DOI: https://doi.org/10.1109/ACCESS.2024.3365742
G. Michelet and F. Breitinger, ‘ChatGPT, Llama, can you write my report? An experiment on assisted digital forensics reports written using (local) large language models, Forensic Science International: Digital Investigation, vol. 48, p. 301683, Mar. 2024, doi: 10.1016/j.fsidi.2023.301683. DOI: https://doi.org/10.1016/j.fsidi.2023.301683
H. Luo et al., ‘WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct’, Aug. 2023.
H. Yang, X.-Y. Liu, and C. D. Wang, ‘FinGPT: Open-Source Financial Large Language Models’, Jun. 2023. DOI: https://doi.org/10.2139/ssrn.4489826
R. Luo et al., ‘BioGPT: generative pre-trained transformer for biomedical text generation and mining’, Brief Bioinform, vol. 23, no. 6, Nov. 2022, doi: 10.1093/bib/bbac409. DOI: https://doi.org/10.1093/bib/bbac409
Y. Labrak, A. Bazoge, E. Morin, P.-A. Gourraud, M. Rouvier, and R. Dufour, ‘BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains’, Feb. 2024. DOI: https://doi.org/10.18653/v1/2024.findings-acl.348
R. Puri and B. Catanzaro, ‘Zero-shot Text Classification With Generative Language Models’, Dec. 2019.
K. Singhal et al., ‘Towards Expert-Level Medical Question Answering with Large Language Models’, May 2023.
P. Colombo et al., ‘SaulLM-7B: A pioneering Large Language Model for Law’, Mar. 2024.
J. Cui et al., ‘Chatlaw: A Multi-Agent Collaborative Legal Assistant with Knowledge Graph Enhanced Mixture-of-Experts Large Language Model’, Jun. 2023.
H. Zou et al., ‘TelecomGPT: A Framework to Build Telecom-Specific Large Language Models’, Jul. 2024. DOI: https://doi.org/10.1109/TMLCN.2025.3593184
A. Lozhkov et al., ‘StarCoder 2 and The Stack v2: The Next Generation’, Feb. 2024.
J.-P. Rivera, G. Mukobi, A. Reuel, M. Lamparth, C. Smith, and J. Schneider, ‘Escalation Risks from Language Models in Military and Diplomatic Decision-Making’, in The 2024 ACM Conference on Fairness, Accountability, and Transparency, New York, NY, USA: ACM, Jun. 2024, pp. 836–898. doi: 10.1145/3630106.3658942. DOI: https://doi.org/10.1145/3630106.3658942
T. Matsumoto, Y. Kibi, and T. Kondo, ‘Purpose Model Simulation - Purpose Formation of Multi-stakeholder by Dialog with LLM-Based AI’, 2024, pp. 110–129. doi: 10.1007/978-3-031-59988-0_7. DOI: https://doi.org/10.1007/978-3-031-59988-0_7
B. Rozière et al., ‘Code Llama: Open Foundation Models for Code’, Aug. 2023.
M. Yousef, K. Mohamed, W. Medhat, E. H. Mohamed, G. Khoriba, and T. Arafa, ‘BeGrading: large language models for enhanced feedback in programming education’, Neural Comput Appl, Oct. 2024, doi: 10.1007/s00521-024-10449-y. DOI: https://doi.org/10.1007/s00521-024-10449-y
Z. Shao et al., ‘DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models’, Feb. 2024, [Online]. Available: http://arxiv.org/abs/2402.03300
Z. Azerbayev et al., ‘Llemma: An Open Language Model For Mathematics’, Oct. 2023.
J. Ji et al., ‘GenRec: Large Language Model for Generative Recommendation’, 2024, pp. 494–502. doi: 10.1007/978-3-031-56063-7_42. DOI: https://doi.org/10.1007/978-3-031-56063-7_42
S. S. Sahoo et al., ‘Large language models for biomedicine: foundations, opportunities, challenges, and best practices’, Journal of the American Medical Informatics Association, Apr. 2024, doi: 10.1093/jamia/ocae074. DOI: https://doi.org/10.1093/jamia/ocae074
Z. Schillaci, ‘On-Site Deployment of LLMs’, in Large Language Models in Cybersecurity, Cham: Springer Nature Switzerland, 2024, pp. 205–211. doi: 10.1007/978-3-031-54827-7_23. DOI: https://doi.org/10.1007/978-3-031-54827-7_23
D. Zhang et al., ‘ChemLLM: A Chemical Large Language Model’, Feb. 2024.
X. Zhang and Q. Yang, ‘XuanYuan 2.0: A Large Chinese Financial Chat Model with Hundreds of Billions Parameters’, in Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, New York, NY, USA: ACM, Oct. 2023, pp. 4435–4439. doi: 10.1145/3583780.3615285. DOI: https://doi.org/10.1145/3583780.3615285
S. Ni et al., ‘MoZIP: A Multilingual Benchmark to Evaluate Large Language Models in Intellectual Property’, Feb. 2024.
M. Juuti, S. Szyller, S. Marchal, and N. Asokan, ‘PRADA: Protecting Against DNN Model Stealing Attacks’, in 2019 IEEE European Symposium on Security and Privacy (EuroS&P), IEEE, Jun. 2019, pp. 512–527. doi: 10.1109/EuroSP.2019.00044. DOI: https://doi.org/10.1109/EuroSP.2019.00044
R. Taylor et al., ‘Galactica: A Large Language Model for Science’, Nov. 2022.
Y. Yao, J. Duan, K. Xu, Y. Cai, Z. Sun, and Y. Zhang, ‘A Survey on Large Language Model (LLM) Security and Privacy: The Good, The Bad, and The Ugly’, High-Confidence Computing, vol. 4, no. 2, p. 100211, Jun. 2024, doi: 10.1016/j.hcc.2024.100211.
J. Wang and P. Srikantha, ‘Stealthy Black-Box Attacks on Deep Learning Non-Intrusive Load Monitoring Models’, IEEE Trans Smart Grid, vol. 12, no. 4, pp. 3479–3492, Jul. 2021, doi: 10.1109/TSG.2021.3062722. DOI: https://doi.org/10.1109/TSG.2021.3062722
Y. Wang, J. Liu, X. Chang, R. J. Rodríguez, and J. Wang, ‘DI-AA: An interpretable white-box attack for fooling deep neural networks’, Inf Sci (N Y), vol. 610, pp. 14–32, Sep. 2022, doi: 10.1016/j.ins.2022.07.157. DOI: https://doi.org/10.1016/j.ins.2022.07.157
W. Wu et al., ‘Practical and Efficient Model Extraction of Sentiment Analysis APIs’, in 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE), IEEE, May 2023, pp. 524–536. doi: 10.1109/ICSE48619.2023.00054. DOI: https://doi.org/10.1109/ICSE48619.2023.00054
F. Alwahedi, A. Aldhaheri, M. A. Ferrag, A. Battah, and N. Tihanyi, ‘Machine learning techniques for IoT security: Current research and future vision with generative AI and large language models’, Internet of Things and Cyber-Physical Systems, vol. 4, pp. 167–185, 2024, doi: 10.1016/j.iotcps.2023.12.003. DOI: https://doi.org/10.1016/j.iotcps.2023.12.003
D. Sahabandu, J. S. Mertoguno, and R. Poovendran, ‘A Natural Language Processing Approach for Instruction Set Architecture Identification’, IEEE Transactions on Information Forensics and Security, vol. 18, pp. 4086–4099, 2023, doi: 10.1109/TIFS.2023.3288456. DOI: https://doi.org/10.1109/TIFS.2023.3288456
Md. A. Rahman, L. Alqahtani, A. Albooq, and A. Ainousah, ‘A Survey on Security and Privacy of Large Multimodal Deep Learning Models: Teaching and Learning Perspective’, in 2024 21st Learning and Technology Conference (L& T), IEEE, Jan. 2024, pp. 13–18. doi: 10.1109/LT60077.2024.10469434. DOI: https://doi.org/10.1109/LT60077.2024.10469434
Y. Yao, J. Duan, K. Xu, Y. Cai, Z. Sun, and Y. Zhang, ‘A Survey on Large Language Model (LLM) Security and Privacy: The Good, The Bad, and The Ugly’, High-Confidence Computing, vol. 4, no. 2, p. 100211, Jun. 2024, doi: 10.1016/j.hcc.2024.100211. DOI: https://doi.org/10.1016/j.hcc.2024.100211
K. Sivamayil, E. Rajasekar, B. Aljafari, S. Nikolovski, S. Vairavasundaram, and I. Vairavasundaram, ‘A Systematic Study on Reinforcement Learning Based Applications’, Energies (Basel), vol. 16, no. 3, p. 1512, Feb. 2023, doi: 10.3390/en16031512. DOI: https://doi.org/10.3390/en16031512
O. A. Alimi, K. Ouahada, and A. M. Abu-Mahfouz, ‘A Review of Machine Learning Approaches to Power System Security and Stability’, IEEE Access, vol. 8, pp. 113512–113531, 2020, doi: 10.1109/ACCESS.2020.3003568. DOI: https://doi.org/10.1109/ACCESS.2020.3003568
C. Rosset, G. Zheng, V. Dibia, A. Awadallah, and P. Bennett, ‘Axiomatic Preference Modeling for Longform Question Answering’, in Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Stroudsburg, PA, USA: Association for Computational Linguistics, 2023, pp. 11445–11475. doi: 10.18653/v1/2023.emnlp-main.702. DOI: https://doi.org/10.18653/v1/2023.emnlp-main.702
S. Agnisarman, S. Lopes, K. Chalil Madathil, K. Piratla, and A. Gramopadhye, ‘A survey of automation-enabled human-in-the-loop systems for infrastructure visual inspection’, Autom Constr, vol. 97, pp. 52–76, Jan. 2019, doi: 10.1016/j.autcon.2018.10.019. DOI: https://doi.org/10.1016/j.autcon.2018.10.019
J. Johnson, ‘Delegating strategic decision-making to machines: Dr. Strangelove Redux?’, Journal of Strategic Studies, vol. 45, no. 3, pp. 439–477, Apr. 2022, doi: 10.1080/01402390.2020.1759038. DOI: https://doi.org/10.1080/01402390.2020.1759038
J. Cleland-Huang, T. Chambers, S. Zudaire, M. T. Chowdhury, A. Agrawal, and M. Vierhauser, ‘Human-Machine Teaming with small Unmanned Aerial Systems in a MAPE-K Environment’, ACM Transactions on Autonomous and Adaptive Systems, Sep. 2023, doi: 10.1145/3618001. DOI: https://doi.org/10.1145/3618001
O. Shahab, B. El Kurdi, A. Shaukat, G. Nadkarni, and A. Soroush, ‘Large language models: a primer and gastroenterology applications’, Therap Adv Gastroenterol, vol. 17, Jan. 2024, doi: 10.1177/17562848241227031. DOI: https://doi.org/10.1177/17562848241227031
Q. Ren et al., ‘CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion’, Mar. 2024. DOI: https://doi.org/10.18653/v1/2024.findings-acl.679
D. Nam, A. Macvean, V. Hellendoorn, B. Vasilescu, and B. Myers, ‘Using an LLM to Help With Code Understanding’, in Proceedings of the IEEE/ACM 46th International Conference on Software Engineering, New York, NY, USA: ACM, Apr. 2024, pp. 1–13. doi: 10.1145/3597503.3639187. DOI: https://doi.org/10.1145/3597503.3639187
Q. Zheng et al., ‘CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X’, in Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, New York, NY, USA: ACM, Aug. 2023, pp. 5673–5684. doi: 10.1145/3580305.3599790. DOI: https://doi.org/10.1145/3580305.3599790
AI@Meta, ‘Llama 3 Model Card’, Meta. Accessed: Jun. 14, 2024. [Online]. Available: https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md
M. A. Ferrag, F. Alwahedi, A. Battah, B. Cherif, A. Mechri, and N. Tihanyi, ‘Generative AI and Large Language Models for Cyber Security: All Insights You Need’, May 2024. DOI: https://doi.org/10.2139/ssrn.4853709
F. Tchakounté, K. Amadou Calvin, A. A. A. Ari, and D. J. Fotsa Mbogne, ‘A smart contract logic to reduce hoax propagation across social media’, Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 6, pp. 3070–3078, Jun. 2022, doi: 10.1016/j.jksuci.2020.09.001. DOI: https://doi.org/10.1016/j.jksuci.2020.09.001
Downloads
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2025 Journal of Novel Engineering Science and Technology
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
