Assessing the Reliability and Hallucination Risks of Large Language  Models

Bhavana Atmaram Vankhede

Assessing the Reliability and Hallucination Risks of Large Language Models

Authors

Bhavana Atmaram Vankhede

Keywords:

Large Language Models, Hallucination, Reliability, Retrieval-Augmented Generation, Trustworthy AI, Factual Consistency

Abstract

Large Language Models (LLMs) have rapidly become central to modern information systems,supporting tasks ranging from customer service to medical question answering and legaldrafting. Despite their fluency, these models frequently generate outputs that appear plausiblebut are factually incorrect, a phenomenon widely referred to as hallucination. This paper investigates the reliability and hallucination risks of contemporary

References

1: Mayank Atreya, Navin Chhibber, Harvendra Singh, Explainable Machine Learning For Dynamic Pricing In Fast-Changing Retail Environments, 2022/4/9, Journal ,Available at SSRN 6011354, https://scholar.google.com/citations?view_op=view_citation&hl=en&user=fyViF1UAAAAJ&citation

_for_view=fyViF1UAAAAJ:LkGwnXOMwfcC.

Downloads

Published

2024-03-20

How to Cite

Bhavana Atmaram Vankhede. (2024). Assessing the Reliability and Hallucination Risks of Large Language Models . Journal of Computational Analysis and Applications (JoCAAA), 33(2), 2315–2325. Retrieved from https://eudoxuspress.com/index.php/pub/article/view/5689