Authors :
Mahadev Dhanaji Limbuche
Volume/Issue :
Volume 11 - 2026, Issue 1 - January
Google Scholar :
https://tinyurl.com/3spms78y
Scribd :
https://tinyurl.com/5d4kx5ae
DOI :
https://doi.org/10.38124/ijisrt/26jan1060
Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.
Abstract :
Large Language Models (LLMs) such as GPT, LLaMA, and PaLM have transformed the field of Natural
Language Processing (NLP) by achieving remarkable results in text generation, summarization, translation, question
answering, and dialogue systems. Their wide adoption across industries highlights their usefulness but also exposes a critical
limitation—hallucination. Hallucination occurs when models generate information that is false, misleading, or fabricated.
These errors can vary from small factual mistakes, like incorrect dates or figures, to serious inaccuracies that may cause
harm in sensitive areas such as healthcare, education, and software development. This paper explores the concept and
classification of hallucinations in LLMs, examines techniques to reduce them—including prompt engineering, fine-tuning,
and Retrieval-Augmented Generation (RAG)—and discusses ethical implications and real-world applications. By
comparing multiple strategies, the study aims to contribute to developing more reliable and trustworthy AI systems.
Keywords :
Large Language Models, Hallucination, Prompt Engineering, Fine-Tuning, Retrieval-Augmented Generation, NLP, AI Ethics, Factual Consistency.
References :
- Open AI. (2023). GPT-4 Technical Report. Open AI.
- Touvron, H., et al. (2023). LLaMA: Open and Efficient Foundation Language Models. arXiv:2302.13971.
- Xu, W., et al. (2024). Hallucination in Large Language Models: A Survey. Journal of Artificial Intelligence Research.
- Lewis, M., et al. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. NeurIPS.
- Bang, Y., et al. (2023). Multitask Prompted Training Enables Zero-Shot Task Generalization. ICLR.
- Zellers, R., et al. (2019). Defending Against Neural Fake News. NeurIPS.
- Bhagavatula, C., et al. (2020). Abstractive Summarization with Faithfulness Constraints. ACL.
- Roller, S., et al. (2021). Recipes for Building an Open-Domain Chatbot. arXiv:2004.13637.
Large Language Models (LLMs) such as GPT, LLaMA, and PaLM have transformed the field of Natural
Language Processing (NLP) by achieving remarkable results in text generation, summarization, translation, question
answering, and dialogue systems. Their wide adoption across industries highlights their usefulness but also exposes a critical
limitation—hallucination. Hallucination occurs when models generate information that is false, misleading, or fabricated.
These errors can vary from small factual mistakes, like incorrect dates or figures, to serious inaccuracies that may cause
harm in sensitive areas such as healthcare, education, and software development. This paper explores the concept and
classification of hallucinations in LLMs, examines techniques to reduce them—including prompt engineering, fine-tuning,
and Retrieval-Augmented Generation (RAG)—and discusses ethical implications and real-world applications. By
comparing multiple strategies, the study aims to contribute to developing more reliable and trustworthy AI systems.
Keywords :
Large Language Models, Hallucination, Prompt Engineering, Fine-Tuning, Retrieval-Augmented Generation, NLP, AI Ethics, Factual Consistency.
