We introduce WordScape, a novel pipeline for the creation of cross-disciplinary, multilingual corpora comprising millions of pages with annotations for document layout detection. Relating visual and textual items on document pages has gained further significance with the advent of multimodal models. Various approaches proved effective for visual question answering or layout segmentation. However, the interplay of text, tables, and visuals remains challenging for a variety of document understanding tasks. In particular, many models fail to generalize well to diverse domains and new languages due to insufficient availability of training data.

Checkboxes are critical in real-world document processing where the presence or absence of ticks directly informs data extraction and decision-making processes. Yet, despite the strong performance of Large Vision and Language Models across a wide range of tasks, they struggle with interpreting checkable content. This challenge becomes particularly pressing in industries where a single overlooked checkbox may lead to costly regulatory or contractual oversights. To address this gap, we introduce the CheckboxQA dataset, a targeted resource designed to evaluate and improve model performance on checkbox-related tasks. It reveals the limitations of current models and serves as a valuable tool for advancing document comprehension systems, with significant implications for applications in sectors such as legal tech and finance. The dataset is publicly available at: https://github.com/Snowflake-Labs/CheckboxQA

Understanding information from visually rich documents remains a significant challenge for traditional Retrieval-Augmented Generation (RAG) methods. Existing benchmarks predominantly focus on image-based question answering (QA), overlooking the fundamental challenges of efficient retrieval, comprehension, and reasoning within dense visual documents. To bridge this gap, we introduce ViDoSeek, a novel dataset designed to evaluate RAG performance on visually rich documents requiring complex reasoning. Based on it, we identify key limitations in current RAG approaches: (i) purely visual retrieval methods struggle to effectively integrate both textual and visual features, and (ii) previous approaches often allocate insufficient reasoning tokens, limiting their effectiveness. To address these challenges, we propose ViDoRAG, a novel multi-agent RAG framework tailored for complex reasoning across visual documents. ViDoRAG employs a Gaussian Mixture Model (GMM)-based hybrid strategy to effectively handle multi-modal retrieval. To further elicit the model's reasoning capabilities, we introduce an iterative agent workflow incorporating exploration, summarization, and reflection, providing a framework for investigating test-time scaling in RAG domains. Extensive experiments on ViDoSeek validate the effectiveness and generalization of our approach. Notably, ViDoRAG outperforms existing methods by over 10% on the competitive ViDoSeek benchmark.

We introduce WordScape, a novel pipeline for the creation of cross-disciplinary, multilingual corpora comprising millions of pages with annotations for document layout detection. Relating visual and textual items on document pages has gained further significance with the advent of multimodal models. Various approaches proved effective for visual question answering or layout segmentation. However, the interplay of text, tables, and visuals remains challenging for a variety of document understanding tasks. In particular, many models fail to generalize well to diverse domains and new languages due to insufficient availability of training data.

The vast portion of workloads employing LLMs involves answering questions grounded on PDF or scan content. We introduce the Arctic-TILT achieving accuracy on par with models 1000$\times$ its size on these use cases. It can be fine-tuned and deployed on a single 24GB GPU, lowering operational costs while processing Visually Rich Documents with up to 400k tokens. The model establishes state-of-the-art results on seven diverse Document Understanding benchmarks, as well as provides reliable confidence scores and quick inference, which are essential for processing files in large-scale or time-sensitive enterprise environments.

Businesses need to query visually rich documents (VRDs) like receipts, medical records, and insurance forms to make decisions. Existing techniques for extracting entities from VRDs struggle with new layouts or require extensive pre-training data. We introduce VRDSynth, a program synthesis method to automatically extract entity relations from multilingual VRDs without pre-training data. To capture the complexity of VRD domain, we design a domain-specific language (DSL) to capture spatial and textual relations to describe the synthesized programs. Along with this, we also derive a new synthesis algorithm utilizing frequent spatial relations, search space pruning, and a combination of positive, negative, and exclusive programs to improve coverage. We evaluate VRDSynth on the FUNSD and XFUND benchmarks for semantic entity linking, consisting of 1,592 forms in 8 languages. VRDSynth outperforms state-of-the-art pre-trained models (LayoutXLM, InfoXLMBase, and XLMRobertaBase) in 5, 6, and 7 out of 8 languages, respectively, improving the F1 score by 42% over LayoutXLM in English. To test the extensibility of the model, we further improve VRDSynth with automated table recognition, creating VRDSynth(Table), and compare it with extended versions of the pre-trained models, InfoXLM(Large) and XLMRoberta(Large). VRDSynth(Table) outperforms these baselines in 4 out of 8 languages and in average F1 score. VRDSynth also significantly reduces memory footprint (1M and 380MB vs. 1.48GB and 3GB for LayoutXLM) while maintaining similar time efficiency.

In recent years, the field of document understanding has progressed a lot. A significant part of this progress has been possible thanks to the use of language models pretrained on large amounts of documents. However, pretraining corpora used in the domain of document understanding are single domain, monolingual, or nonpublic. Our goal in this paper is to propose an efficient pipeline for creating a big-scale, diverse, multilingual corpus of PDF files from all over the Internet using Common Crawl, as PDF files are the most canonical types of documents as considered in document understanding. We analyzed extensively all of the steps of the pipeline and proposed a solution which is a trade-off between data quality and processing time. We also share a CCpdf corpus in a form or an index of PDF files along with a script for downloading them, which produces a collection useful for language model pretraining. The dataset and tools published with this paper offer researchers the opportunity to develop even better multilingual language models.

Current research in form understanding predominantly relies on large pre-trained language models, necessitating extensive data for pre-training. However, the importance of layout structure (i.e., the spatial relationship between the entity blocks in the visually rich document) to relation extraction has been overlooked. In this paper, we propose REgion-Aware Relation Extraction (RE$^2$) that leverages region-level spatial structure among the entity blocks to improve their relation prediction. We design an edge-aware graph attention network to learn the interaction between entities while considering their spatial relationship defined by their region-level representations. We also introduce a constraint objective to regularize the model towards consistency with the inherent constraints of the relation extraction task. Extensive experiments across various datasets, languages and domains demonstrate the superiority of our proposed approach.

Information extraction (IE) from documents is an intensive area of research with a large set of industrial applications. Current state-of-the-art methods focus on scanned documents with approaches combining computer vision, natural language processing and layout representation. We propose to challenge the usage of computer vision in the case where both token style and visual representation are available (i.e native PDF documents). Our experiments on three real-world complex datasets demonstrate that using token style attributes based embedding instead of a raw visual embedding in LayoutLM model is beneficial. Depending on the dataset, such an embedding yields an improvement of 0.18% to 2.29% in the weighted F1-score with a decrease of 30.7% in the final number of trainable parameters of the model, leading to an improvement in both efficiency and effectiveness.