A Systematic Framework for Enterprise Knowledge Retrieval: Leveraging LLM-Generated Metadata to Enhance RAG Systems

TL;DR

This paper introduces a systematic framework using LLM-generated metadata to improve document retrieval in enterprise RAG systems, demonstrating significant accuracy gains and low latency.

Contribution

It presents a structured pipeline for metadata enrichment, evaluating chunking and embedding strategies, and provides empirical evidence of improved retrieval performance.

Findings

Metadata enrichment outperforms content-only baselines.

Recursive chunking with TF-IDF embeddings achieves 82.5% precision.

Naive chunking with prefix-fusion yields NDCG 0.813.

Abstract

In enterprise settings, efficiently retrieving relevant information from large and complex knowledge bases is essential for operational productivity and informed decision-making. This research presents a systematic empirical framework for metadata enrichment using large language models (LLMs) to enhance document retrieval in Retrieval-Augmented Generation (RAG) systems. Our approach employs a structured pipeline that dynamically generates meaningful metadata for document segments, substantially improving their semantic representations and retrieval accuracy. Through a controlled 3 X 3 experimental matrix, we compare three chunking strategies -- semantic, recursive, and naive -- and evaluate their interactions with three embedding techniques -- content-only, TF-IDF weighted, and prefix-fusion -- isolating the contribution of each component through ablation analysis. The results demonstrate that metadata-enriched approaches consistently outperform content-only baselines, with recursive chunking paired with TF-IDF weighted embeddings yielding 82.5% precision and naive chunking with prefix-fusion achieving the strongest ranking quality (NDCG 0.813). Our evaluation employs cross-encoder reranking for silver-standard ground truth generation, with statistical significance confirmed via Bonferroni-corrected paired t-tests. These findings confirm that metadata enrichment improves vector space organization and retrieval effectiveness while maintaining sub-30 ms P95 latency, providing a quantitative decision framework for deploying high-performance, scalable RAG systems in enterprise settings.