A Systematic Framework for Enterprise Knowledge Retrieval: Leveraging LLM-Generated Metadata to Enhance RAG Systems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917370918862848 |
|---|---|
| author | Mishra, Pranav Pushkar Yeole, Kranti Prakash Keshavamurthy, Ramyashree Surana, Mokshit Bharat Sarayloo, Fatemeh |
| author_facet | Mishra, Pranav Pushkar Yeole, Kranti Prakash Keshavamurthy, Ramyashree Surana, Mokshit Bharat Sarayloo, Fatemeh |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_05411 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Systematic Framework for Enterprise Knowledge Retrieval: Leveraging LLM-Generated Metadata to Enhance RAG Systems Mishra, Pranav Pushkar Yeole, Kranti Prakash Keshavamurthy, Ramyashree Surana, Mokshit Bharat Sarayloo, Fatemeh Information Retrieval Artificial Intelligence H.3.3; I.2.7 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. |
| title | A Systematic Framework for Enterprise Knowledge Retrieval: Leveraging LLM-Generated Metadata to Enhance RAG Systems |
| topic | Information Retrieval Artificial Intelligence H.3.3; I.2.7 |
| url | https://arxiv.org/abs/2512.05411 |