{"version":1,"type":"story","url":"https://digestai.news/story/researchers-propose-multi-split-boundary-decision-to-lower-llm-documen","json":"https://digestai.news/story/researchers-propose-multi-split-boundary-decision-to-lower-llm-documen.json","markdown":"https://digestai.news/story/researchers-propose-multi-split-boundary-decision-to-lower-llm-documen.md","slug":"researchers-propose-multi-split-boundary-decision-to-lower-llm-documen","headline":"Researchers propose multi-split boundary decision to lower LLM document segmentation cost","summary":"Scanned mail, PDFs and bundled attachments often arrive as continuous page streams that need to be broken into separate documents before classification, extraction or routing. The paper introduces Multi‑Split Boundary Decision (MSBD), a zero‑shot approach that lets a large language model predict several document boundaries inside a single page window, cutting the number of inference calls required.\n\nThe authors test MSBD on a variety of language models, document collections, input types and window sizes. Results show that, within a model‑ and corpus‑specific window range, MSBD retains strong segmentation accuracy while markedly improving inference efficiency. Larger windows, however, cause a rapid drop in performance, with distinct patterns of over‑ and under‑segmentation that differ across models. The study demonstrates that choosing an appropriate window size lets practitioners achieve a favorable accuracy‑efficiency trade‑off for zero‑shot page‑stream segmentation.","keyPoints":["MSBD predicts multiple document boundaries per LLM call, reducing inference requests","Experiments show MSBD keeps high segmentation accuracy while boosting efficiency within a model‑ and corpus‑dependent window range","Accuracy declines sharply when window sizes grow too large, with over‑ and under‑segmentation varying by model"],"whyItMatters":"Cutting inference calls lowers compute costs for organizations that process large volumes of scanned or PDF documents, speeding up downstream AI workflows such as classification and data extraction.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":[],"models":[],"people":[]},"firstPublishedAt":"2026-09-22T04:00:00Z","updatedAt":"2026-09-22T04:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.AI","title":"Splitting Documents at Lower Cost: Multi-Split Boundary Decisions for LLM-Based Page Stream Segmentation","url":"https://arxiv.org/abs/2609.22620","publishedAt":"2026-09-22T04:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Researchers propose multi-split boundary decision to lower LLM document segmentation cost\", 22 September 2026, https://digestai.news/story/researchers-propose-multi-split-boundary-decision-to-lower-llm-documen","publisher":"Digest AI","title":"Researchers propose multi-split boundary decision to lower LLM document segmentation cost","datePublished":"2026-09-22T04:00:00Z","url":"https://digestai.news/story/researchers-propose-multi-split-boundary-decision-to-lower-llm-documen"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}