Citation

Mohamed, Yousef and Foo, Yee Loo (2025) Countering AI Hallucination by Utilizing a Concept-Aware Model. In: 2025 Multimedia University Engineering Conference (MECON), 21-23 July 2025, Cyberjaya, Malaysia.

Text IEEE Xplore Full-Text PDF_42.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

This paper showcase how to reduce artificial intelligence hallucination by making information retrieval and task execution more efficient, AI-based virtual assistants have revolutionized organizational communication. However, they are still susceptible to hallucinations, which can result in outputs that are confidently expressed but inaccurate or deceptive. Current defenses, like context enrichment and rulebased filters, produce inconsistent outcomes and uneven accuracy, which erodes efficiency and confidence. To significantly lower hallucinations, we present a hybrid framework that combines uncertainty-aware screening with a multi-stage self-familiarity model. While Bayesian deep learning and Monte Carlo dropout quantify response confidence and allow the system to verify or withhold uncertain answers, the self-familiarity component strengthens conceptual understanding across processing stages. Our method improves overall communication effectiveness in organizational settings, increases user trust, and produces more accurate and dependable responses.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	AI hallucination prevention
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines
Divisions:	Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	18 Mar 2026 04:27
Last Modified:	18 Mar 2026 04:48
URII:	http://shdl.mmu.edu.my/id/eprint/15533

Downloads

Edit (login required)