International Journal on Science and Technology

E-ISSN: 2229-7677   •   Impact Factor: 9.88

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 17 Issue 2 April-June 2026 Submit your research before last 3 days of June to publish your research paper in the issue of April-June.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 17 Issue 2
April-June 2026

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

System-Level Strategies for Mitigating Hallucinations in LLM-Based Applications

Author(s) Ronak Indrasinh Kosamia
Country United States
Abstract Large Language Models (LLMs) are increasingly integrated into production software systems including enterprise assistants, developer tools, financial applications, and information retrieval platforms. Despite their capabilities, LLMs frequently generate hallucinated responses—outputs that appear plausible but contain factually incorrect or unsupported information. Such hallucinations present significant reliability and safety challenges when LLMs are deployed in high-stakes environments.

While many existing approaches attempt to reduce hallucinations through model training improvements, production deployments often require system-level safeguards that operate independently of the model architecture. This paper examines architectural strategies for mitigating hallucinations in LLM-based applications. We analyze mitigation mechanisms including retrieval-augmented generation, verification pipelines, tool-augmented reasoning, and multi-model consensus architectures.

We propose a layered guardrail architecture that integrates knowledge retrieval, response verification, and confidence scoring to reduce hallucination propagation in production systems. Experimental evaluation demonstrates that combining retrieval grounding with verification pipelines significantly reduces hallucination rates while preserving response quality.
The results suggest that reliable deployment of LLM-based applications requires system-level architectural controls rather than reliance on model improvements alone.
Keywords large language models, hallucination mitigation, retrieval-augmented generation, AI system architecture, reliable AI systems
Field Engineering
Published In Volume 15, Issue 1, January-March 2024
Published On 2024-02-03
DOI https://doi.org/10.71097/IJSAT.v15.i1.11135
View / Download PDF File

Share this


CrossRef

CrossRef DOI is assigned to each research paper published in our journal.

IJSAT DOI prefix is
10.71097/IJSAT

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 17 Isu 2Cover Page Vol 17 Isu 1Cover Page Vol 16 Isu 4

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About IJSAT
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us Message on WhatsApp +91-9687-182-185 editor@ijsat.org