Retrieval-Augmented Multi-LLM Ensemble for Industrial Part Specification Extraction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Mohammed, Muzakkiruddin Ahmed, Talburt, John R., Claasssens, Leon, Marais, Adriaan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912810610458624
author Mohammed, Muzakkiruddin Ahmed
Talburt, John R.
Claasssens, Leon
Marais, Adriaan
author_facet Mohammed, Muzakkiruddin Ahmed
Talburt, John R.
Claasssens, Leon
Marais, Adriaan
contents Industrial part specification extraction from unstructured text remains a persistent challenge in manufacturing, procurement, and maintenance, where manual processing is both time-consuming and error-prone. This paper introduces a retrieval-augmented multi-LLM ensemble framework that orchestrates nine state-of-the-art Large Language Models (LLMs) within a structured three-phase pipeline. RAGsemble addresses key limitations of single-model systems by combining the complementary strengths of model families including Gemini (2.0, 2.5, 1.5), OpenAI (GPT-4o, o4-mini), Mistral Large, and Gemma (1B, 4B, 3n-e4b), while grounding outputs in factual data using FAISS-based semantic retrieval. The system architecture consists of three stages: (1) parallel extraction by diverse LLMs, (2) targeted research augmentation leveraging high-performing models, and (3) intelligent synthesis with conflict resolution and confidence-aware scoring. RAG integration provides real-time access to structured part databases, enabling the system to validate, refine, and enrich outputs through similarity-based reference retrieval. Experimental results using real industrial datasets demonstrate significant gains in extraction accuracy, technical completeness, and structured output quality compared to leading single-LLM baselines. Key contributions include a scalable ensemble architecture for industrial domains, seamless RAG integration throughout the pipeline, comprehensive quality assessment mechanisms, and a production-ready solution suitable for deployment in knowledge-intensive manufacturing environments.
format Preprint
id arxiv_https___arxiv_org_abs_2601_05266
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Retrieval-Augmented Multi-LLM Ensemble for Industrial Part Specification Extraction
Mohammed, Muzakkiruddin Ahmed
Talburt, John R.
Claasssens, Leon
Marais, Adriaan
Information Retrieval
Artificial Intelligence
Computation and Language
Machine Learning
Industrial part specification extraction from unstructured text remains a persistent challenge in manufacturing, procurement, and maintenance, where manual processing is both time-consuming and error-prone. This paper introduces a retrieval-augmented multi-LLM ensemble framework that orchestrates nine state-of-the-art Large Language Models (LLMs) within a structured three-phase pipeline. RAGsemble addresses key limitations of single-model systems by combining the complementary strengths of model families including Gemini (2.0, 2.5, 1.5), OpenAI (GPT-4o, o4-mini), Mistral Large, and Gemma (1B, 4B, 3n-e4b), while grounding outputs in factual data using FAISS-based semantic retrieval. The system architecture consists of three stages: (1) parallel extraction by diverse LLMs, (2) targeted research augmentation leveraging high-performing models, and (3) intelligent synthesis with conflict resolution and confidence-aware scoring. RAG integration provides real-time access to structured part databases, enabling the system to validate, refine, and enrich outputs through similarity-based reference retrieval. Experimental results using real industrial datasets demonstrate significant gains in extraction accuracy, technical completeness, and structured output quality compared to leading single-LLM baselines. Key contributions include a scalable ensemble architecture for industrial domains, seamless RAG integration throughout the pipeline, comprehensive quality assessment mechanisms, and a production-ready solution suitable for deployment in knowledge-intensive manufacturing environments.
title Retrieval-Augmented Multi-LLM Ensemble for Industrial Part Specification Extraction
topic Information Retrieval
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2601.05266