Metraipolis › archive › dc_805aa845cf91

Beyond Similarity Search: Knowledge Graph Metadata Enrichment for Enterprise Retrieval-Augmented Generation — arXiv:2610.37728

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.37728
License (as archived)
CC0-1.0
Archived
2026-10-31T06:11:02.415Z
SHA-256 of the archived text
b40141dbbe4041a2a81960bac1c801b59cf9a6210c13557f7845d5ee8d3b92de
Stable URL of this page
https://metraipolis.com/documento/dc_805aa845cf91

How to cite

Beyond Similarity Search: Knowledge Graph Metadata Enrichment for Enterprise Retrieval-Augmented Generation — arXiv:2610.37728 — arXiv (en), https://arxiv.org/abs/2610.37728 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_805aa845cf91 (Metraipolis archive dc_805aa845cf91, sha256 b40141dbbe4041a2a81960bac1c801b59cf9a6210c13557f7845d5ee8d3b92de)
BibTeX
@misc{dc805aa845cf91,
  title = {Beyond Similarity Search: Knowledge Graph Metadata Enrichment for Enterprise Retrieval-Augmented Generation — arXiv:2610.37728},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.37728},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_805aa845cf91; sha256 b40141dbbe4041a2a81960bac1c801b59cf9a6210c13557f7845d5ee8d3b92de},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.37728. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A key challenge of RAG systems is retrieving information from enterprise documents created by multiple teams over time, where it is not possible to enrich the information using the latest information and metadata available outside the scope of organizational documentation responsibility. We investigated whether using a knowledge graph to store metadata and frequently changing information would improve upon knowledge retrieval over similarity search over embeddings. To perform the experiment, we created a snapshot of the SEC EDGAR dataset for a quarter, comprising 167,050 filings from 10,511 companies and 508,714 embedded chunks of risk-factor text. To simulate the enrichment, we created a knowledge graph of 430,257 nodes and 561,144 edges carrying an accession number on every edge. To evaluate the gain obtained via a graph-based design, we evaluated three architectures: text-to-SQL over typed columns, dense-vector RAG with HNSW cosine search, and a two-stage GraphRAG design. All architectures share the same model and temperature to allow comparison. Results are scored programmatically by an LLM as judge over 20 questions divided across four categories, each question asked three times. GraphRAG solved 16 of 20 questions on all three attempts, compared to 10 for text-to-SQL and 3 for vector RAG. GraphRAG lost on structured aggregation queries. Vector RAG lost the single-document category it was expected to win, passing 3 of 15 where GraphRAG passed 15 of 15, because company attribution is not recoverable from cosine similarity at this scale. All six confident falsehoods in the benchmark were text-to-SQL conflating distinct people who share a surname, the failure that resolving identity to an identifier before reading any text prevents structurally; GraphRAG made none. We claim no advantage beyond this corpus, this model and this question set.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.37728 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T06:07:08.590Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).