Configurable Semantic Chunking for Biomedical Information Extraction in Retrieval-Augmented Generation
2026-08-31 • Computation and Language
Computation and LanguageInformation Retrieval
AI summaryⓘ
The authors propose a new way to break down biomedical text into meaningful pieces for information extraction, improving on a previous method called BioMedRAG that used fixed-size chunks. Their approach uses smarter rules that keep important entities and relationships intact, which helps the system better understand and extract complex information. They tested this approach on several biomedical datasets and found it works especially well when the text clearly signals relationships. This new method can be easily adjusted and understood because it uses configurable settings instead of rigid chunk sizes.
retrieval-augmented generationbiomedical information extractionchunkingentity recognitionrelation extractionF1 scoreBioMedRAGsemantic chunkingdataset evaluationadverse event classification
Authors
Riya Ahuja, Tim Kacprowski, Roya Shiasi Sardoabi
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.