Configurable Semantic Chunking for Biomedical Information Extraction in Retrieval-Augmented Generation
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.
Riya Ahuja, Tim Kacprowski, Roya Shiasi Sardoabi Institute of Data Science in Biomedicine et al.
· 0 citations