# Splitting Documents at Lower Cost: Multi-Split Boundary Decisions for LLM-Based Page Stream Segmentation

arXiv: https://arxiv.org/abs/2609.22620 · HTML: https://mlsanity.com/paper/2609.22620/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 27 references that are in the map.
- First posted on arXiv 18 Sep 2026.

## Builds on (most cited first, 5 of 5)

- [Batch Prompting: Efficient Inference with Large Language Model APIs](https://mlsanity.com/paper/2301.08721/) (2023)
- [VRDU: A Benchmark for Visually-rich Document Understanding](https://mlsanity.com/paper/2211.15421/) (2022)
- [Large Language Models for Page Stream Segmentation](https://mlsanity.com/paper/2408.11981/) (2024)
- [DocSplit: A Comprehensive Benchmark Dataset and Evaluation Approach for Document Packet Recognition and Splitting](https://mlsanity.com/paper/2602.15958/) (2026)
- [CoSMo: A Multimodal Transformer for Page Stream Segmentation in Comic Books](https://mlsanity.com/paper/2507.10053/) (2025)

## Abstract (arXiv)

Scanned mail, uploaded PDFs, and consolidated attachments often arrive as page streams that must be split into individual documents before downstream classification, extraction, or routing. Zero-shot large language models can detect document boundaries without task-specific training, but standard Page Classification (PC) and Boundary Decision (BD) formulations resolve only one boundary per model call. We introduce Multi-Split Boundary Decision (MSBD), which predicts multiple boundaries within a page window in a single call, reducing the number of inference requests. We evaluate MSBD across multiple language models, document collections, input modalities, and window sizes. The results reveal a model- and corpus-dependent operating range in which MSBD preserves strong segmentation accuracy while substantially improving inference efficiency, followed by a sharp decline at larger windows. MSBD provided the strongest overall accuracy--efficiency trade-off, while large windows expose distinct over- and under-segmentation behavior across models. These findings show that multi-boundary prediction can make zero-shot page stream segmentation more efficient when the window size is selected for the target corpus.