Knowledge Economy Studies

A Review of Methods for Reducing Hallucinations in Generative Artificial Intelligence to Enhance Knowledge Economy

Document Type : Original Article

Author

Zahra Roozbahani

Assistant Professor, Department of Computer Engineering, National University of Skills (NUS), Tehran, Iran.

https://doi.org/10.22034/kes.2025.2049560.1042
Abstract
Generative Artificial Intelligence (AI) models, such as large language models, are transforming various sectors of the knowledge economy, including education, research, development, and data analysis, due to their ability to generate new contents. However, hallucination, which refers to the generation of content that appears plausible but lacks scientific basis, presents a significant challenge to the safe adoption of this technology in critical applications such as financial analysis and market prediction. This study aims to explore the effects of hallucinations on productivity of the knowledge economy and proposes some approaches to mitigate them. Through conducting a systematic literature review and qualitative analysis, different types of hallucinations in generative AI models are identified, and their effects on trust and productivity in knowledge-based systems are examined. The review of hallucination reduction methods indicates that the approaches utilizing reinforcement learning with human feedback enhance the reliability of the generated content by correcting errors in the model’s output through repeated adjustments. Finally, this study presents a hybrid approach to hallucination reduction in knowledge economy. This approach is based on three techniques of prompt engineering, retrieval-based generation, and self-improvement through feedback and reasoning. The results provide a foundation for future research on managing AI risks and enhancing the productivity of the knowledge economy.

Keywords

Generative AI
Hallucination
Knowledge Economy
Large Language Models
Trust

Subjects

Alghanemi, J., & Al Mubarak, M. (2022). The role of artificial intelligence in knowledge management. In Studies in Computational Intelligence. Future of Organizations and Work after the 4th Industrial Revolution (pp. 359–373). 10.1007/978-3-030-99000-8_20.
Amayuelas, A., Wong, K., Pan, L., Chen, W., & Wang, W. (2023). Knowledge of knowledge: Exploring known-unknowns uncertainty with large language models. ArXiv preprint arXiv:2305.13712.
Bian, N., Liu, P., Han, X., Lin, H., Lu, Y., He, B., & Sun, L. (2023). A drop of ink may make a million think: The spread of false information in large language models. ArXiv preprint arXiv:2305.04812.
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., … Amodei, D. (2020). Language Models are Few-Shot Learners. Retrieved from http://arxiv.org/abs/2005.14165.
Farquhar, S., Kossen, J., Kuhn, L., & Gal, Y. (2024). Detecting hallucinations in large language models using semantic entropy. Nature, 630(8017), 625–630. 10.1038/s41586-024-07421-0.
Feldman, P., Foulds, J. R., & Pan, S. (2023). Trapping LLM hallucinations using tagged context prompts. Retrieved from http://arxiv.org/abs/2306.06085.
Feuerriegel, S., Hartmann, J., Janiesch, C., & Zschech, P. (2024). Generative AI. Business & Information Systems Engineering, 66(1), 111-126.
Gunjal, A., Yin, J., & Bas, E. (2023). Detecting and preventing hallucinations in Large Vision Language Models. Retrieved from http://arxiv.org/abs/2308.06394.
Kanaani, M., Dadkhah, S., & Ghorbani, A. A. (2024, May). Triple-R: Automatic Reasoning for Fact Verification Using Language Models. In N. Calzolari, M.-Y. Kan, V. Hoste, A. Lenci, S. Sakti, & N. Xue (Eds.), Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) (pp. 16831–16840). Retrieved from https://aclanthology.org/2024.lrec-main.1463.
Kang, H., Ni, J., & Yao, H. (2023). Ever: Mitigating hallucination in large Language Models through real-time Verification and rectification. Retrieved from http://arxiv.org/abs/2311.09114.
Khamassi, M., Nahon, M., & Chatila, R. (2024). Strong and weak alignment of large language models with human values. Sci Rep, 14, 19399. https://doi.org/10.1038/s41598-024-70031-3.
Köpf, A., Kilcher, Y., von Rütte, D., Anagnostidis, S., Tam, Z.-R., Stevens, K., … Mattick, A. (2024). OpenAssistant conversations - democratizing large language model alignment. Article 2064. Presented at the Proceedings of the 37th International Conference on Neural Information Processing Systems, New Orleans, LA, USA. Curran Associates Inc.
Li, M., Peng, B., Galley, M., Gao, J., & Zhang, Z. (2023). Self-Checker: Plug-and-play modules for fact-checking with large language models. Retrieved from http://arxiv.org/abs/2305.14623.
Ma, J., Dai, D., Sha, L., & Sui, Z. (2024). Large language models are unconscious of unreasonability in math problems. ArXiv preprint arXiv:2403.19346.
Madaan, A., Tandon, N., Gupta, P., Hallinan, S., Gao, L., Wiegreffe, S., … Clark, P. (2023). Self-refine: Iterative refinement with Self-feedback. 10.48550/ARXIV.2303.17651.
Mardiansyah, K., & Surya, W. (2024). Comparative analysis of ChatGPT-4 and Google Gemini for spam detection on the SpamAssassin public mail corpus. 10.21203/rs.3.rs-4005702/v1.
Mayahi, S., & Vidrih, M. (2022). The impact of generative AI on the future of visual content marketing. 10.48550/ARXIV.2211.12660.
Molina, M. G., & Chicaíza, L. (2011). A Guide to Sources for Research in Economic                     Sciences. Social Science Research Network. https://doi.org/10.2139/SSRN.1766062.
Mündler, N., He, J., Jenko, S., & Vechev, M. (2023). Self-contradictory hallucinations of large language models: Evaluation, detection and mitigation. Retrieved from http://arxiv.org/abs/2305.15852.
Peng, B., Galley, M., He, P., Cheng, H., Xie, Y., Hu, Y., … Gao, J. (2023). Check your facts and try again: Improving large language models with external knowledge and automated feedback. Retrieved from http://arxiv.org/abs/2302.12813.
Qiu, Y., Ziser, Y., Korhonen, A., Ponti, E. M., & Cohen, S. B. (2023). Detecting and mitigating hallucinations in multilingual summarisation. Retrieved from http://arxiv.org/abs/2305.13632.
Ramnarayan, S. (2021). Marketing and artificial intelligence. In Advances in Marketing, Customer Relationship Management, and E-Services (pp. 75–95). 10.4018/978-1-7998-5077-9.ch005.
Ray, P. P. (2023). Chatgpt: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope. Internet of Things and Cyber-Physical Systems, 3, 121–154.
Saxena, S., Prasad, S., Prakash, M. V., Shankar, A., Vaddina, V., & Gopalakrishnan, S. (2023). Minimizing factual inconsistency and hallucination in large language models. arXiv preprint arXiv:2311.13878.
Schulhoff, S., Ilie, M., Balepur, N., Kahadze, K., Liu, A., Si, C., Li, Y., Gupta, A., Han, H., & Schulhoff, S. (n.d.), (2024). The Prompt Report A Systematic Survey of Prompting Techniques. https://arxiv.org/abs/2406.06608.
Si, C., Gan, Z., Yang, Z., Wang, S., Wang, J., Boyd-Graber, J., & Wang, L. (2022). Prompting GPT-3 to be reliable. Retrieved from http://arxiv.org/abs/2210.09150.
Teimuraz Goderdzishvili, T. G. (2023). Artificial intelligence and creative thinking, the future of idea generation. Economics, 105(3–4), 63–73. 10.36962/ecs105/3-4/2023-63.
Tu, C.-H., Hsu, H.-J., & Chen, S.-W. (2024). Reinforcement learning for optimized information retrieval in LLaMA. 10.21203/rs.3.rs-3847100/v1.
Vima, C., Bosch, H., & Harringstone, J. (2024). Enhancing inference efficiency and accuracy in large language models through next-phrase prediction. 10.21203/rs.3.rs-4864441/v1.
White, J., Fu, Q., Hays, S., Sandborn, M., Olea, C., Gilbert, H., … Schmidt, D. C. (2023). A prompt pattern catalog to enhance prompt engineering with ChatGPT. Retrieved from http://arxiv.org/abs/2302.11382.
Yan, Y., Zheng, P., & Wang, Y. (2024). Enhancing large language model capabilities for rumor detection with Knowledge-Powered Prompting. Engineering Applications of Artificial Intelligence, 133(108259), 108259. 10.1016/j.engappai.2024.108259.
Yin, Z. (2024). A review of methods for alleviating hallucination issues in large language models. Applied and Computational Engineering, 76, 258-266.
Yu, L., & Lai, Z. (2021). The management of internet content products in the era of artificial intelligence. Journal of Physics. Conference Series, 1757(1), 012017. 10.1088/1742-6596/1757/1/012017.
Yuji, Zhang., Sha, Li., Jiateng, Liu., Pengfei, Yu., Yi, R., Fung., Jing, Li., Manling, Li., Heng, Ji. (2024). Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models. Retrieved from arXiv:2407.08039v1. https://doi.org/10.48550/arXiv.2407.08039.
Knowledge Economy Studies
Volume 2, Issue 1
April 2025
Pages 21-34

Home

Submit Manuscript

Contact Us