04:00
2026-09-23
arxiv.org
large-language-models
Splitting Documents at Lower Cost: Multi-Split Boundary Decisions for LLM-Based Page Stream Segmentation
A new arXiv paper (2609.22620v1) introduces Multi-Split Boundary Decision (MSBD), a method that predicts multiple document boundaries within a page window in a single large language model call, reduciβ¦