Architecting Trustworthy LLMs: A Unified TRUST Framework for Mitigating AI Hallucination
Journal of Computer Science and Frontier Technologies · 2025-11-10 · 1 (3) · 1
DOI: 10.63313/jcsft.9019 ↗At a glance
Journal article in Journal of Computer Science and Frontier Technologies, published online on 2025-11-10. Written by Lingyi Meng. Cited 3 times so far (Crossref); 28 references. The full text is freely available (open access, CC BY 4.0).
Abstract (original language)
The use of large language models (LLMs) in high-stakes domains like engi-neer-ing and public policy is hindered by their tendency to halluci-nate—generating factually incorrect or unverifiable information. Although technical mitigations such as Retrieval-Augmented Generation (RAG) and Re-inforcement Learning from Human Feedback (RLHF) exist, they are typically applied as isolated point-solutions, lacking a unifying framework. This paper analyses the archi-tectural roots of AI hallucination, classifying them into cog-nitive gaps and sta-tistical biases, and then shows the shortcomings in current mitigation strategies. To address this, we introduce the TRUST model, which is a systematic structure built on five interconnected pillars: Transparency, Relia-bility, Uncertainty, Su-pervision, and Traceability. The TRUST framework serves as the architectural basis to orchestrate existing technologies and establish ac-countability in the lifecycle of AI and to build robust and accountable AIs for vital societal applica-tions [2].
Cite
APA
Meng, L. (2025). Architecting Trustworthy LLMs: A Unified TRUST Framework for Mitigating AI Hallucination. Journal of Computer Science and Frontier Technologies, 1(3), 1. https://doi.org/10.63313/jcsft.9019
Vancouver
Meng L. Architecting Trustworthy LLMs: A Unified TRUST Framework for Mitigating AI Hallucination. Journal of Computer Science and Frontier Technologies. 2025;1(3):1. doi:10.63313/jcsft.9019
BibTeX
@article{Meng2025,
author = {Meng, Lingyi},
title = {Architecting Trustworthy LLMs: A Unified TRUST Framework for Mitigating AI Hallucination},
journal = {Journal of Computer Science and Frontier Technologies},
year = {2025},
volume = {1},
number = {3},
pages = {1},
doi = {10.63313/jcsft.9019}
}
EUVIMED