Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM66913
Volume:
10 |
8 |
Aug 2026
Pages:
1-18
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Engineering
University of Petroleum & Energy Studies
Generative AI has moved rapidly from experimentation into enterprise products. Organizations are using Large Language Models (LLMs) for employee assistants, customer support, knowledge search, software engineering, document processing, content generation, analytics, and decision support. However, the methods traditionally used to assure software quality were not designed for systems that generate probabilistic outputs. A conventional software application can often be validated against deterministic expected results : given input X, the application should produce output Y. A GenAI application may produce several acceptable responses to the same input. It may also produce a fluent, confident and completely incorrect response. Its behavior can change when the underlying model, prompt, retrieval data, system instructions, safety configuration or surrounding application changes.
KEYWORDS
GenAI quality goes beyond traditional testing and requires a multidimensional quality approach. Organizations must evaluate accuracy, robustness, safety, security, transparency, and business value. Traditional QA should evolve into continuous AI Quality Engineering. Quality must be measurable, risk-based, and continuously monitored in production. Cross-functional ownership is essential to building trustworthy AI products. The goal is not just capable AI, but safe, reliable, explainable, and business-ready AI. Trustworthy GenAI Quality Engineering is the foundation for responsible enterprise AI adoption.
GenAI quality goes beyond traditional testing and requires a multidimensional quality approach. Organizations must evaluate accuracy, robustness, safety, security, transparency, and business value. Traditional QA should evolve into continuous AI Quality Engineering. Quality must be measurable, risk-based, and continuously monitored in production. Cross-functional ownership is essential to building trustworthy AI products. The goal is not just capable AI, but safe, reliable, explainable, and business-ready AI. Trustworthy GenAI Quality Engineering is the foundation for responsible enterprise AI adoption.
Publication Date
8/24/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
1
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...