Unsupervised Document and Template Clustering using Multimodal Embeddings

• URL: http://arxiv.org/abs/2506.12116v3
• Date: Sun, 26 Oct 2025 20:20:07 GMT
• Title: Unsupervised Document and Template Clustering using Multimodal Embeddings
• Authors: Phillipe R. Sampaio, Helene Maxcici,
• Abstract summary: We study unsupervised clustering of documents at both the category and template levels using frozen multimodal encoders and classical clustering algorithms.<n>We evaluate eight encoders (text-only, layout-aware, vision-only, and vision-language) with $k$-Means, DBSCAN, HDBSCAN + $k$-NN, and BIRCH on five corpora spanning clean synthetic invoices, their heavily degraded print-and-scan counterparts, scanned receipts, and real identity and certificate documents.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study unsupervised clustering of documents at both the category and template levels using frozen multimodal encoders and classical clustering algorithms. We systematize a model-agnostic pipeline that (i) projects heterogeneous last-layer states from text-layout-vision encoders into token-type-aware document vectors and (ii) performs clustering with centroid- or density-based methods, including an HDBSCAN + $k$-NN assignment to eliminate unlabeled points. We evaluate eight encoders (text-only, layout-aware, vision-only, and vision-language) with $k$-Means, DBSCAN, HDBSCAN + $k$-NN, and BIRCH on five corpora spanning clean synthetic invoices, their heavily degraded print-and-scan counterparts, scanned receipts, and real identity and certificate documents. The study reveals modality-specific failure modes and a robustness-accuracy trade-off, with vision features nearly solving template discovery on clean pages while text dominates under covariate shift, and fused encoders offering the best balance. We detail a reproducible, oracle-free tuning protocol and the curated evaluation settings to guide future work on unsupervised document organization.

Related papers

• DocDjinn: Controllable Synthetic Document Generation with VLMs and Handwriting Diffusion [5.342168661302001]
  We propose a novel framework for controllable synthetic document generation using Vision-Language Models (VLMs)<n>Our approach generates visually plausible and semantically consistent synthetic documents that follow the distribution of an existing source dataset.<n>We show that our framework achieves on average $87%$ of the performance of the full real-world dataset.
  arXiv  Detail & Related papers  (2026-02-25T11:52:13Z)
• Do not be greedy, Think Twice: Sampling and Selection for Document-level Information Extraction [19.989502176674183]
  Document-level Information Extraction (DocIE) aims to produce an output template with the entities and relations of interest occurring in the given document.<n>Standard practices include prompting decoder-only LLMs using greedy decoding to avoid output variability.<n>We show that sampling can produce substantially better solutions than greedy decoding, especially when using reasoning models.
  arXiv  Detail & Related papers  (2026-01-26T11:53:08Z)
• DAVE: A VLM Vision Encoder for Document Understanding and Web Agents [50.05119785399764]
  We introduce DAVE, a vision encoder purpose-built for Vision-language models (VLMs)<n>Our training pipeline is designed to leverage abundant unlabeled data to bypass the need for costly large-scale annotations for document and web images.<n>We use ensemble training to fuse features from pretrained generalist encoders with our own document and web-specific representations.
  arXiv  Detail & Related papers  (2025-12-19T04:09:24Z)
• DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLM [35.910677096654574]
  Document parsing aims to transform unstructured PDF images into semi-structured data, facilitating the digitization and utilization of information in diverse domains.<n>Common practice often selects the top-performing model on standard benchmarks.<n>We introduce DOCR-Inspector, which formalizes document parsing assessment as fine-grained error detection and analysis.
  arXiv  Detail & Related papers  (2025-12-11T13:16:33Z)
• MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns [80.05126590825121]
  MonkeyOCR v1.5 is a unified vision-language framework that enhances both layout understanding and content recognition.<n>To address complex table structures, we propose a visual consistency-based reinforcement learning scheme.<n>Two specialized modules, Image-Decoupled Table Parsing and Type-Guided Table Merging, are introduced to enable reliable parsing of tables.
  arXiv  Detail & Related papers  (2025-11-13T15:12:17Z)
• Hybrid Topic-Semantic Labeling and Graph Embeddings for Unsupervised Legal Document Clustering [1.6267479602370543]
  This paper proposes a hybrid approach for classifying legal texts by combining unsupervised topic and graph embeddings with a supervised model.<n>We employ Top2Vec to learn semantic document embeddings and automatically discover latent topics, and Node2Vec to capture structural relationships via a bipartite graph of legal documents.<n>Our computations on a legal document dataset demonstrate that the combined Top2Vec+Node2Vec approach improves clustering quality over text-only or graph-only embeddings.
  arXiv  Detail & Related papers  (2025-08-31T20:53:59Z)
• Docopilot: Improving Multimodal Models for Document-Level Understanding [87.60020625241178]
  We present a high-quality document-level dataset, Doc-750K, designed to support in-depth understanding of multimodal documents.<n>This dataset includes diverse document structures, extensive cross-page dependencies, and real question-answer pairs derived from the original documents.<n>Building on the dataset, we develop a native multimodal model, Docopilot, which can accurately handle document-level dependencies without relying on RAG.
  arXiv  Detail & Related papers  (2025-07-19T16:03:34Z)
• Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning [58.16354555208417]
  PAD and FFD are proposed to protect face data from physical media-based Presentation Attacks and digital editing-based DeepFakes, respectively.<n>The lack of a Unified Face Attack Detection model to simultaneously handle attacks in these two categories is mainly attributed to two factors.<n>We present a novel Visual-Language Model-based Hierarchical Prompt Tuning Framework that adaptively explores multiple classification criteria from different semantic spaces.
  arXiv  Detail & Related papers  (2025-05-19T16:35:45Z)
• Relation-Rich Visual Document Generator for Visual Information Extraction [12.4941229258054]
  We propose a Relation-rIch visual Document GEnerator (RIDGE) that addresses these limitations through a two-stage approach.<n>Our method significantly enhances the performance of document understanding models on various VIE benchmarks.
  arXiv  Detail & Related papers  (2025-04-14T19:19:26Z)
• Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking [58.69615583599489]
  Deliberate Thinking based Retriever (Debater) is a novel approach that enhances document representations by incorporating a step-by-step thinking process.<n>Debater significantly outperforms existing methods across several retrieval benchmarks.
  arXiv  Detail & Related papers  (2025-02-18T15:56:34Z)
• MMDocIR: Benchmarking Multi-Modal Retrieval for Long Documents [26.39534684408116]
  This work introduces a new benchmark, named MMDocIR, that encompasses two distinct tasks: page-level and layout-level retrieval.<n>The MMDocIR benchmark comprises a rich dataset featuring 1,685 questions annotated by experts and 173,843 questions with bootstrapped labels.
  arXiv  Detail & Related papers  (2025-01-15T14:30:13Z)
• Unified Multimodal Interleaved Document Representation for Retrieval [57.65409208879344]
  We propose a method that holistically embeds documents interleaved with multiple modalities.<n>We merge the representations of segmented passages into one single document representation.<n>We show that our approach substantially outperforms relevant baselines.
  arXiv  Detail & Related papers  (2024-10-03T17:49:09Z)
• Leveraging Collection-Wide Similarities for Unsupervised Document Structure Extraction [61.998789448260005]
  We propose to identify the typical structure of document within a collection. We abstract over arbitrary header paraphrases, and ground each topic to respective document locations. We develop an unsupervised graph-based method which leverages both inter- and intra-document similarities.
  arXiv  Detail & Related papers  (2024-02-21T16:22:21Z)
• Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation [59.37587762543934]
  This paper studies the problem of weakly open-vocabulary semantic segmentation (WOVSS) Existing methods suffer from a granularity inconsistency regarding the usage of group tokens. We propose the prototypical guidance network (PGSeg) that incorporates multi-modal regularization.
  arXiv  Detail & Related papers  (2023-10-29T13:18:00Z)
• Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction [30.827288164068992]
  Token Path Prediction (TPP) is a simple prediction head to predict entity mentions as token sequences within documents. TPP models the document layout as a complete directed graph of tokens, and predicts token paths within the graph as entities. For better evaluation of VrD-NER systems, we also propose two revised benchmark datasets of NER on scanned documents.
  arXiv  Detail & Related papers  (2023-10-17T06:08:55Z)
• DocumentNet: Bridging the Data Gap in Document Pre-Training [78.01647768018485]
  We propose a method to collect massive-scale and weakly labeled data from the web to benefit the training of VDER models. The collected dataset, named DocumentNet, does not depend on specific document types or entity sets. Experiments on a set of broadly adopted VDER tasks show significant improvements when DocumentNet is incorporated into the pre-training.
  arXiv  Detail & Related papers  (2023-06-15T08:21:15Z)
• Mining both Commonality and Specificity from Multiple Documents for Multi-Document Summarization [1.4629756274247374]
  The multi-document summarization task requires the designed summarizer to generate a short text that covers the important information of original documents. This paper proposes a multi-document summarization approach based on hierarchical clustering of documents.
  arXiv  Detail & Related papers  (2023-03-05T14:25:05Z)
• Large-Scale Multi-Document Summarization with Information Extraction and Compression [31.601707033466766]
  We develop an abstractive summarization framework independent of labeled data for multiple heterogeneous documents. Our framework processes documents telling different stories instead of documents on the same topic. Our experiments demonstrate that our framework outperforms current state-of-the-art methods in this more generic setting.
  arXiv  Detail & Related papers  (2022-05-01T19:49:15Z)
• Unified Pretraining Framework for Document Understanding [52.224359498792836]
  We present UDoc, a new unified pretraining framework for document understanding. UDoc is designed to support most document understanding tasks, extending the Transformer to take multimodal embeddings as input. An important feature of UDoc is that it learns a generic representation by making use of three self-supervised losses.
  arXiv  Detail & Related papers  (2022-04-22T21:47:04Z)
• Multi-View Document Representation Learning for Open-Domain Dense Retrieval [87.11836738011007]
  This paper proposes a multi-view document representation learning framework. It aims to produce multi-view embeddings to represent documents and enforce them to align with different queries. Experiments show our method outperforms recent works and achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2022-03-16T03:36:38Z)
• Multilevel Text Alignment with Cross-Document Attention [59.76351805607481]
  Existing alignment methods operate at a single, predefined level. We propose a new learning approach that equips previously established hierarchical attention encoders for representing documents with a cross-document attention component.
  arXiv  Detail & Related papers  (2020-10-03T02:52:28Z)
• Towards a Multi-modal, Multi-task Learning based Pre-training Framework for Document Representation Learning [5.109216329453963]
  We introduce Document Topic Modelling and Document Shuffle Prediction as novel pre-training tasks. We utilize the Longformer network architecture as the backbone to encode the multi-modal information from multi-page documents in an end-to-end fashion.
  arXiv  Detail & Related papers  (2020-09-30T05:39:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.