aiqbench analysis
This research presents CoVe-RAG+, a framework that significantly reduces hallucinations in Large Language Models by integrating Chain-of-Verification with Retrieval-Augmented Generation for high-stakes engineering tasks. By enabling iterative self-verification against external authoritative sources like CAD data and simulation reports, the method achieves a 28% improvement in factual accuracy over baseline approaches. This advancement is critical for deploying trustworthy AI systems in precision-dependent fields such as Computer-Aided Design and standards compliance verification.
Reducing Hallucinations in Large Language Models Through Integrated Self-Verification and Retrieval-Augmented Generation
arXiv:2609.26229v1 Announce Type: cross Abstract: Large Language Models (LLMs) are progressively used for advanced engineering tasks, includes Computer-Aided Design (CAD) documentation, standards compliance verification, and knowledge retrieval. Still, they are prone to produce hallucinations, outputs that seem convincing but aren't based on context that limit their trustworthiness in high-end engineering applications where precision and compliance are crucial. The paper introduces CoVe-RAG+, a unified framework that integrates Chain-of-Verification (CoVe) with Retrieval-Augmented Generation (RAG) to mitigate hallucinations in the results generated by large language models (LLMs). CoVe-RAG+ supports LLM verification in external sources of authority, such as engineering standards, CAD information, and simulation reports, while applying an iterative self-verification process to validate important claims. CoVe-RAG+ is assessed on engineering activities such as CAD model documentation, standards compliance verification, and the reutilization of historical design data. Experimental findings indicate a 28% improvement in factual accuracy relative to baseline CoVe and RAG methodologies. Moreover, CoVe-RAG+ strengthens user confidence by providing elucidative verification reports and source traceability. The findings indicate that CoVe-RAG+ provides a scalable and reliable option for implementing LLMs in engineering design processes where factual accuracy is critical.
Abstract:Large Language Models (LLMs) are progressively used for advanced engineering tasks, includes Computer-Aided Design (CAD) documentation, standards compliance verification, and knowledge retrieval. Still, they are prone to produce hallucinations, outputs that seem convincing but aren't based on context that limit their trustworthiness in high-end engineering applications where precision and compliance are crucial. The paper introduces CoVe-RAG+, a unified framework that integrates Chain-of-Verification (CoVe) with Retrieval-Augmented Generation (RAG) to mitigate hallucinations in the results generated by large language models (LLMs). CoVe-RAG+ supports LLM verification in external sources of authority, such as engineering standards, CAD information, and simulation reports, while applying an iterative self-verification process to validate important claims. CoVe-RAG+ is assessed on engineering activities such as CAD model documentation, standards compliance verification, and the reutilization of historical design data. Experimental findings indicate a 28% improvement in factual accuracy relative to baseline CoVe and RAG methodologies. Moreover, CoVe-RAG+ strengthens user confidence by providing elucidative verification reports and source traceability. The findings indicate that CoVe-RAG+ provides a scalable and reliable option for implementing LLMs in engineering design processes where factual accuracy is critical.
Software Engineering (cs.SE); Artificial Intelligence (cs.AI)
I.2.7; H.3.3; I.2.6; J.6
arXiv:2609.26229 [cs.SE]
(or arXiv:2609.26229v1 [cs.SE] for this version)
https://doi.org/10.48550/arXiv.2609.26229 arXiv-issued DOI via DataCite (pending registration)
Proceedings of the ASME 2025 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (IDETC/CIE2025), Anaheim, CA, USA, August 17-20, 2025, Paper No. DETC2025-169730, V02BT02A032
https://doi.org/10.1115/DETC2025-169730 DOI(s) linking to related resources
Full text under the publisher's open licence · 239 words
