Skip to content

Configurable Semantic Chunking for Biomedical Information Extraction in Retrieval-Augmented Generation

Aug 2026 · 0 citations · 16 references
Computer Science

TL;DR

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.

Abstract

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.

View source

Similar papers

BELXTR: Biomedical Entity Linking via Contextualized Token Retrieval

BELXTR is presented, a novel embedding model based on the multi-vector (a.k.a. late interaction) architecture, which allows to leverage token-level matching information in biomedical entity linking by integrating an existing task-specific training objective and exploring active query expansion.

Samuele Garda, U. Leser · 0 citations
Open access 2026

Effective Chunking for Retrieval-Augmented Generation over Structured Institutional Documents

Evaluating four chunking strategies for structured institutional RAG systems demonstrates that chunking strategies influence RAG objectives in distinct ways, with structure-aware chunking improving answer generation while semantic chunking more effectively preserving table integrity.

Siti Sarah Izhan Khalib, Abdul Hadi Abd Rahman, L. Zakaria · 0 citations
#small language model Open access Sep 2026

Biomedical retrieval-augmented generation for relation classification

The rapid expansion of biomedical literature requires automated methods for accurate and efficient information extraction. This study addresses relation classification: given a pair of annotated biomedical entities in a research article title and abstract, assigning the relation that holds between them from a pre-defin...

Jannat, Charlie Dil, Tom Arodz et al. · 0 citations
Conference Aug 2026

Hierarchical Multi-Layer Reranking Approach for Biomedical Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) for domain-specific tasks such as medical question answering. However, recent reviews of RAG applications in the medical domain indicate that issues such as retrieval noise remain and require further investigation into mitigation strategies, wit...

Fadhilah Ramadhan, Rexton Amadeo Onggo, Karto Iskandar · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.