Metraipolis › archive › dc_45329ea1fa6e

Improving Contextual Retrieval for Long Documents using Semantic Chunking and Hybrid Retrieval Strategies — arXiv:2611.08498

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08498
License (as archived)
CC0-1.0
Archived
2026-11-09T22:36:04.858Z
SHA-256 of the archived text
71434b9f6c70ca4b3a1d4fe445220c5019bcbb4afc79df2a51bc46f598e1ae1c
Stable URL of this page
https://metraipolis.com/documento/dc_45329ea1fa6e

How to cite

Improving Contextual Retrieval for Long Documents using Semantic Chunking and Hybrid Retrieval Strategies — arXiv:2611.08498 — arXiv (en), https://arxiv.org/abs/2611.08498 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_45329ea1fa6e (Metraipolis archive dc_45329ea1fa6e, sha256 71434b9f6c70ca4b3a1d4fe445220c5019bcbb4afc79df2a51bc46f598e1ae1c)
BibTeX
@misc{dc45329ea1fa6e,
  title = {Improving Contextual Retrieval for Long Documents using Semantic Chunking and Hybrid Retrieval Strategies — arXiv:2611.08498},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08498},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_45329ea1fa6e; sha256 71434b9f6c70ca4b3a1d4fe445220c5019bcbb4afc79df2a51bc46f598e1ae1c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08498. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The vast amount of information available in lengthy, distributed documents makes finding relevant answers difficult, especially when the answer requires connecting evidence from multiple sources. Standard Retrieval-Augmented Generation (RAG) systems often struggle with this type of "multi-hop" reasoning and frequently face issues with context fragmentation. In this paper, we propose a hybrid RAG framework that integrates the structured reasoning of knowledge graphs with the broad semantic coverage of dense vector retrieval. Our approach employs a multi-stage pipeline using transformer-based summarization and semantic chunking to improve context retention. We construct a dynamic knowledge graph to capture explicit relationships between entities while simultaneously maintaining a dense vector index. During inference, the system uses a hierarchical mechanism that prioritizes graph traversal for precision and falls back to vector retrieval when necessary. We evaluated our framework on the MultiHop-RAG dataset. The results show that this hybrid approach outperforms standalone vector and graph-based baselines, achieving higher Exact Match scores and improved retrieval accuracy for complex queries. This confirms that merging structured reasoning with standard vector retrieval creates a more robust system for handling complex knowledge-intensive questions.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR) ; Computation and Language (cs.CL); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.08498 — 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 2026-11-09T22:31:01.953Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).