Metraipolis › archive › dc_8e90ae53fe58

Configurable Semantic Chunking for Biomedical Information Extraction in Retrieval-Augmented Generation — arXiv:2608.31139

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.31139
License (as archived)
CC0-1.0
Archived
2026-10-17T08:07:57.293Z
SHA-256 of the archived text
593cc57fc1fec4d51abb04b94ea493728ec7913d708b19eac59b12be49700620
Stable URL of this page
https://metraipolis.com/documento/dc_8e90ae53fe58

How to cite

Configurable Semantic Chunking for Biomedical Information Extraction in Retrieval-Augmented Generation — arXiv:2608.31139 — arXiv (en), https://arxiv.org/abs/2608.31139 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8e90ae53fe58 (Metraipolis archive dc_8e90ae53fe58, sha256 593cc57fc1fec4d51abb04b94ea493728ec7913d708b19eac59b12be49700620)
BibTeX
@misc{dc8e90ae53fe58,
  title = {Configurable Semantic Chunking for Biomedical Information Extraction in Retrieval-Augmented Generation — arXiv:2608.31139},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.31139},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8e90ae53fe58; sha256 593cc57fc1fec4d51abb04b94ea493728ec7913d708b19eac59b12be49700620},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.31139. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

BioMedRAG introduced retrieval-augmented generation with a learned chunk scorer for biomedical information extraction. However, it relies on fixed-size chunking which can fragment semantic evidence. We propose a configurable semantic chunking framework that addresses this limitation by combining entity-preserving windows, trigger-centered chunking, proposition-first extraction, tiered trigger prioritization, and hierarchical relation resolution. The framework integrates with BioMedRAG by replacing only the chunk construction stage while preserving the embedding model, learned chunk scorer, generator, and evaluation protocol. We evaluate the framework on biomedical relation extraction benchmarks (GM-CIHT, DDI, ChemProt) and adverse event classification (ADE). On GM-CIHT, the full hybrid configuration achieves 82.6% F1, improving over the fixed-size baseline (74.2% F1) by 8.4 points under our experimental setup. Cross-dataset analysis shows that semantic chunking improves extraction datasets with explicit relation cues, such as GM-CIHT and DDI, while fixed chunking remains competitive or stronger for dense biochemical extraction and binary classification settings such as ChemProt and ADE. By externalizing chunking logic into configuration files, the framework provides an interpretable and adaptable alternative to rigid fixed-size chunking for biomedical RAG pipelines.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2608.31139 — 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 2026-10-17T07:47:52.891Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).