mlsanityData to 7 Oct 2026

Large Language Models for Page Stream Segmentation

arXiv 2408.11981 ↗First posted 21 Aug 2024cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

Page Stream Segmentation (PSS) is an essential prerequisite for automated document processing at scale. However, research progress has been limited by the absence of realistic public benchmarks. This paper works towards addressing this gap by introducing TABME++, an enhanced benchmark featuring commercial Optical Character Recognition (OCR) annotations. We evaluate the performance of large language models (LLMs) on PSS, focusing on decoder-based models fine-tuned with parameter-efficient methods. Our results show that decoder-based LLMs outperform smaller multimodal encoders. Through a review of existing PSS research and datasets, we identify key challenges and advancements in the field. Our findings highlight the key importance of robust OCR, providing valuable insights for the development of more effective document processing systems.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 24 of its 52 references that are in the map. First posted on arXiv 21 Aug 2024.

Builds on

24 of 52 references.

References · 24

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  5. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  6. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  7. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,883
  8. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,288
  9. 2019LayoutLM: Pre-training of Text and Layout for Document Image Understandingcited by 549
  10. 2022LayoutLMv3: Pre-training for Document AI with Unified Text and Image Maskingcited by 481
  11. 2022DiT: Self-supervised Pre-training for Document Image Transformercited by 152
  12. 2022LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understandingcited by 107
12 more
  1. 2018Text Segmentation as a Supervised Learning Taskcited by 76
  2. 2019ICDAR 2019 Competition on Scene Text Visual Question Answeringcited by 46
  3. 2022OCR-IDL: OCR Annotations for Industry Document Library Datasetcited by 35
  4. 2023Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answeringcited by 24
  5. 2024From Text Segmentation to Smart Chaptering: A Novel Benchmark for Structuring Video Transcriptionscited by 16
  6. 2020Multi-Modal Reasoning Graph for Scene-Text Based Fine-Grained Image Classification and Retrievalcited by 10
  7. 2023Beyond Document Page Classification: Design, Datasets, and Challengescited by 10
  8. 2023Testing the Depth of ChatGPT's Comprehension via Cross-Modal Tasks Based on ASCII-Art: GPT3.5's Abilities in Regard to Recognizing and Generating ASCII-Art Are Not Totally Lackingcited by 7
  9. 2024Notes on Applicability of GPT-4 to Document Understandingcited by 7
  10. 2022Semantic Parsing of Interpage Relationscited by 4
  11. 2022Sequence-aware multimodal page classification of Brazilian legal documentscited by 3
  12. 2024Large Language Models Understand Layoutcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025CoSMo: A Multimodal Transformer for Page Stream Segmentation in Comic Bookscited by 2
  2. 2026GutenOCR: A Grounded Vision-Language Front-End for Documentscited by 2
  3. 2026PubMed-OCR: PMC Open Access OCR Annotationscited by 0
  4. 2026Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Formscited by 0
  5. 2026Splitting Documents at Lower Cost: Multi-Split Boundary Decisions for LLM-Based Page Stream Segmentationcited by 0