Document Information Extraction

Follow this topic Ask about this topic

Momentum

34 papers in the last four weeks, up 89% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 189

May 31, 2026cs.CL

Peacemaker at ATE-IT: Automatic term extraction from Italian text for waste management data using encoder model

The development of automatic term extraction has become increasingly important in modern technology. Automatic term extraction can be found in virtually every search engine that is currently available to users. Recent advancements have provided promising results for the extraction of automatic terms; however, accurate labeling is difficult because of several factors, such as the limited number of annotated documents available for training and the complexity of extracting multi-word expressions due to shifts in the domain. In this paper, we will present a low-cost and interpretable method of automatic term extraction, developed specifically for Task A of the ATE Shared Task. This new method utilizes fine-tuning extraction strategies that can run on a small amount of computational resources. We evaluated our automated system using both type-level and micro-level measures of precision, recall, and F1-score to measure both complementary aspects of the extraction performance. According to the experimental results, our proposed approach achieves consistent and balanced performance compared to other teams. Even though the technique itself is relatively straightforward, it serves as a good starting point for low-resource models. Overall, the findings point toward the possibility of significant future advancements (in model expansion) with higher-level performance still able to retain their ability to be interpreted.

Mahdi Bakhtiyarzadeh, Hadi Bayrami Asl Tekanlou, Jafar Razmara

Department of Computer Science, University of Tabriz, 29 Bahman Boulevard, Tabriz 51666-16471, Iran

Document Information Extraction Low-Resource Language Processing

May 31, 2026cs.DL

Digging Up Citations: FOSSIL, a Dataset and Workflow for Reference Extraction in Law and the Humanities

Citation extraction tools are designed for the structured end-of-document bibliographies of the natural sciences, but law and humanities scholarship cites references primarily in footnotes, where bibliographic data is interleaved with commentary and cross-references and varies widely across languages and styles. To address the scarcity of suitable gold-standard resources, we present FOSSIL (Footnote-based Open-access SSH Scientific Instance Labels), an openly licensed multilingual dataset of 96 annotated scholarly articles containing over 7,600 footnote-embedded references, together with PDF-TEI Editor (a collaborative web annotation tool), a documented seven-annotator workflow, and a Grobid specialization for footnote-based citations. In end-to-end evaluation, the specialized pipeline nearly doubles extraction quality over default Grobid (micro-F1 from 0.36 to 0.72), driven largely by improved recall, while showing that substantial headroom remains for cross-references and mixed-content footnotes. This extended abstract presents work in progress; annotations of citations segmentation and parsing, and cross-reference resolution are ongoing.

Luca Foppiano, Christian Boulanger

ScienciaLAB, Portugal · Max Planck Institute for Legal History and Legal Theory, Germany

Document Information Extraction Legal Document Analysis

May 29, 2026cs.CL

Wind Turbine Maintenance Log Labelling Framework: LLM-Driven Data Correction and Enrichment via Semantic Extraction of Reliability Intelligence

As wind turbine fleets age, data-driven reliability engineering is essential to optimise their operation and maintenance for service life extension and levelised cost of energy reduction. Failure event descriptions within historical maintenance logs are a source of valuable reliability intelligence. However, they typically appear as unstructured natural language entries, rendering them inaccessible for quantitative analysis. This paper presents a novel methodology leveraging a large language model (LLM) to systematically standardise and structure maintenance logs based on their free-text descriptors. Operating on a dataset of 16,316 maintenance logs from 280 turbines monitored over nine years, the developed model-agnostic framework autonomously corrected hierarchical system codes and extracted evidence-based taxonomies of maintenance actions and failure modes. The automated pipeline successfully structured over 70% of the dataset. It resolved pervasive misclassification issues, such as isolating previously unclassified pitch system faults and restoring missing system codes, and enriched the records by applying empirical taxonomies to label specific actions taken and failure modes addressed. By using system-based log batches to construct empirical dictionaries of failure modes, observable symptoms, dominant mechanisms, and candidate causes, this approach reduces the inherent subjectivity of manual failure modes and effects analysis (FMEA). Ultimately, the methodology provides a highly scalable, cost-effective blueprint for translating large sets of qualitative field observations into quantitative reliability metrics, laying the foundation for integrated root-cause analysis across the renewable energy sector, improved FMEA, and advanced predictive maintenance.

Max Malyi, Jonathan Shek, Alasdair McDonald +1

Institute for Energy Systems, School of Engineering, The University of Edinburgh, Edinburgh, UK · 2Nadara, Lisbon, Portugal

LLM-Assisted Annotation Document Information Extraction Predictive Maintenance LLM Information Extraction

May 29, 2026cs.CY

Traceable by Design: An LLM Pipeline and Dashboard for EU Regulatory Consultation Analysis

Public consultations generate large volumes of data in the form of stakeholder submissions that are practically unfeasible to analyse manually. We present an end-to-end LLM-based pipeline and interactive dashboard for structured topic extraction from regulatory consultation submissions, demonstrated on the European Commission's Digital Fairness Act (DFA) public call for evidence as a case study. The system processes raw PDF attachments and web-form responses, extracts topic annotations, and grounds every extraction in a verbatim quote from the source text. Applied to 4,322 DFA submissions, the pipeline produced 15,368 topic annotations supported by 20,951 verbatim evidence quotes. Three principles govern the proposed design: verbatim grounding, full traceability, and transparency by design. The dashboard exposes the full extraction dataset through five analytical views, from dataset-level topic overviews to individual paragraph drill-downs, with every result traceable to its source. Beyond the predefined DFA topic categories, the pipeline generated certain stakeholder concerns, such as Age Verification, Payment Processor Censorship, and Digital Ownership, that a fixed-taxonomy approach would have missed. The pipeline is domain-generic; adapting it to a new consultation requires only a prompt update and a new dataset. A live demo is available at https://dfa-dashboard.thalesbertaglia.com/. The code and processed data are publicly available at https://github.com/thalesbertaglia/dfa-dashboard.

Thales Bertaglia, Haoyang Gui, Catalina Goanta +1

Utrecht University, The Netherlands · Maastricht University, The Netherlands

LLM-Assisted Annotation Document Information Extraction Legal Document Analysis LLM Information Extraction

May 28, 2026cs.CL

AI for Monitoring and Classifying Data Used in Research Literature

While platforms like Google Scholar and Semantic Scholar track citations for academic papers, no comparable infrastructure exists for monitoring dataset usage in research literature, leaving the landscape of data use largely opaque. Addressing this gap is critical for transparency, reproducibility, and monitoring of impact, yet progress is hindered by inconsistent citation practices, scarce labeled data, and ambiguous references to datasets in the wild. Traditional NLP approaches struggle with these challenges, motivating the shift toward more adaptive, semantically rich models. Building on prior work using LLMs for data mention detection and synthetic data for bootstrapping training, this paper presents an updated methodology for scalable dataset monitoring. We introduce a multitask GLiNER-based framework that jointly performs dataset mention extraction, relation identification, and usage-context classification. To address label scarcity, the pipeline leverages synthetic data generation to produce training examples and LLM-based revalidation to filter incorrect mentions and enforce labeling consistency, together improving reliability, coverage, and output consistency across the training pipeline. This work advances the development of open-source tools for monitoring data use in research literature, contributing to the broader goal of generalizable, unconstrained dataset citation tracking.

Rafael Macalaba, Aivin V. Solatorio

Development Data Group Office of the World Bank Group Chief Statistician The World Bank 1818 H Street N.W., Washington, 20433 District of Columbia, USA

Document Information Extraction LLM Information Extraction

May 28, 2026cs.AI

Compass: Navigating Global Marine Lead Data Integration through Expert-Guided LLM Agent

Marine lead (Pb) and its isotopes are critical tracers for ocean circulation and anthropogenic pollution, yet in-situ observations remain costly and sparse. While vast historical records exist, they lie buried within the unstructured content of academic papers, creating "data silos" inaccessible to comprehensive analysis. Manual extraction is unscalable, while general-purpose Large Language Models (LLMs) lack the necessary domain-specific knowledge, leading to hallucinations and scientifically invalid outputs. To address this, we introduce an expert-guided adaptation approach that enables LLMs to perform rigorous scientific data extraction without fine-tuning. We operationalize this approach through Compass, an LLM agent framework enhanced by a Knowledge Tree co-designed with marine scientists, which decomposes complex tasks into verifiable steps, guiding the agent's reasoning to ensure scientific validity. Deploying Compass across a corpus of over 230,000 relevant open-access papers, we successfully extract 3,751 previously unincorporated Pb records. This effort establishes the largest integrated marine Pb database to date. Beyond standard metrics, Compass demonstrates superior reliability through multi-layered validation, achieving 92% accuracy as confirmed through expert manual verification. The newly integrated data expand coverage in previously under-sampled regions such as the East China Sea and the Southern Ocean, providing an enriched data foundation for future scientific discoveries. We release an interactive visualization platform to facilitate open scientific access. Our work demonstrates that expert-guided agents can effectively bridge the gap between general-purpose LLMs and high-stakes scientific domains, enabling scalable data discovery in geosciences.

Yiming Liu, Bin Lu, Meng Jin +6

AI Agents for Scientific Discovery Document Information Extraction LLM Information Extraction

May 27, 2026cs.CL

IPO-Mine: A Toolkit and Dataset for Section-Structured Analysis of Long, Multimodal IPO Documents

An Initial Public Offering (IPO) filing is a document released when a private firm goes public, allowing individual (retail) investors to purchase its shares. These filings describe a firm's business, financials, and risks and are long, multimodal documents with narrative text and images. Despite their importance to financial markets, there is no large-scale, standardized dataset or benchmark for studying IPO filings with modern language and multimodal models. These documents pose significant challenges: filings frequently exceed 500,000 tokens and lack consistent structural organization. We introduce the IPO-Toolkit, an open-source framework for downloading and parsing IPO filings into standardized section-structured text and extracted images. The toolkit segments filings, extracts embedded images, and produces structured outputs that enable large-scale, reproducible analysis workflows over long, multimodal documents. Using this infrastructure, we construct the IPO-Dataset, a large, section-structured, multimodal dataset covering more than 109,000 IPO filings and amendments from 1994 to 2026 and containing over 76,000 images. We establish structured evaluation tasks over extracted financial charts, including chart quality and misleadingness assessment. Our experiments show that state-of-the-art multimodal models often diverge from expert human judgments on these tasks, exposing alignment challenges in multimodal reasoning over long, real-world regulatory documents. Beyond benchmarking, the IPO-Dataset enables large-scale analysis of section-level textual variation and cross-industry differences in visual and textual disclosure practices. Our code, dataset, and website are publicly available under CC-BY-4.0.

Michael Galarnyk, Siddharth Lohani, Vidhyakshaya Kannan +8

Georgia Institute of Technology Atlanta, GA, USA · Sai University Chennai, Tamil Nadu, India · Duke University Durham, NC, USA

Document Information Extraction Multimodal Model Evaluation Finance Multimodal Learning

May 26, 2026cs.CL

Self-Ensembling Vision-Language Models for Chart Data Extraction

Charts effectively convey quantitative information, but the underlying data are often locked in image form, hindering reuse and analysis. Manually digitizing charts is time-consuming and error-prone, motivating automatic chart-to-table extraction. Recent approaches use specialized vision-language models (VLMs), yet performance still lags on charts with many datapoints or substantial stylistic variation. We propose a VLM self-ensembling method that repeatedly samples multiple tabular outputs from the same VLM for a fixed chart image and aggregates them at the level of individual table cells. We align candidate tables and take per-cell medians over numerical values to produce a more accurate consensus table. Our method also includes convergence detection to stop sampling once the aggregated table stabilizes, and uncertainty estimation based on dispersion across samples to help users assess extraction reliability. Because existing chart extraction benchmarks contain relatively simple plots with limited room for improvement, we introduce WB-ChartExtract, a new benchmark built from World Bank data with more complex and stylistically diverse charts; on average, its charts contain 7 times more datapoints than those in the ChartQA benchmark. Across both ChartQA and WB-ChartExtract, our approach improves extraction accuracy over single-pass VLM outputs, yielding up to 23% relative improvement on WB-ChartExtract after ensembling. More broadly, our method helps unlock tabular data previously siloed in chart images, enabling downstream analysis and reuse.

Thomas Berkane, Qianyi Wang, Maimuna S. Majumder

Computational Health Informatics Program, Boston Children’s Hospital & Harvard Medical School

Data Visualization Ensemble Learning Document Information Extraction Chart Data Extraction Chart Understanding

May 26, 2026cs.CL

Reliable Extraction of Clinical Follow-Up Instructions: A Hybrid Neural-Symbolic Pipeline

Objective. Outpatient notes carry follow-up instructions pairing actions with future times ("MRI brain in two weeks"). Extracting (action, date) pairs supports scheduling and audit, but generative extractors miss the date because linking and arithmetic are implicit in decoding. We test a hybrid neural-symbolic pipeline against direct generation. Methods. We define TestSpecification and TimeSpecification entities and a ScheduledFor relation. BioBERT feeds BIO tagging and a biaffine linker; entities are canonicalized via a 28-action ontology and times normalized to day offsets deterministically. We evaluate on a 2,000-note synthetic outpatient corpus with action-disjoint splits (18 train, 6 OOV-test) against zero-shot GPT-4o-mini and LoRA-fine-tuned LLaMA-3 8B with note-level bootstrap 95% CIs. Results. On 259-note seen and OOV splits the hybrid pipeline achieves Test-Time Pair F1 of 0.997 and 0.986 with 0.00-day MAE. Baselines reach high action F1 (LLaMA-3 0.992; GPT-4o-mini 0.963 seen) but Pair F1 stays at 0.51-0.57 (LLaMA-3) and 0.53 (GPT-4o-mini), CIs non-overlapping with the hybrid. Conclusion. Separating learned entity extraction from deterministic date arithmetic outperforms generation on this benchmark, generalizes to held-out actions, and exposes failure modes. Transfer to real EHR notes is the next validation; a first-pass realism check is in Limitations.

Michal Laufer, Yehudit Aperstein, Alexander Apartsin

1Bar-Ilan University, Ramat Gan, Israel · 2Afeka College of Engineering, Tel Aviv, Israel · 3Holon Institute of Technology, Holon, Israel

Relation Extraction Healthcare Document Information Extraction Clinical Information Extraction Neuro-Symbolic AI

May 25, 2026cs.CR

TTPrint: Evidence-Grounded TTP Extraction via Diverge-then-Converge Verification

Extracting MITRE ATT&CK techniques from cyber threat intelligence (CTI) reports is an open-set, multi-label problem requiring both high recall (not missing techniques) and high precision (not hallucinating unsupported ones). Existing methods--rule-based, supervised, and LLM-based--struggle to achieve both: rule-based and supervised approaches lack generalizability across diverse attack descriptions, while LLM-based approaches that couple candidate generation and validation within a single inference step suffer from limited recall and precision simultaneously. We propose TTPrint, which addresses this challenge through a diverge-then-converge design inspired by how human analysts work: first extracting broadly, then verifying rigorously. In the divergent phase, reports are decomposed into atomic behaviors and candidate techniques are proposed broadly. A deterministic span localization stage then anchors each candidate to a specific evidence window in the source text. A convergent verification stage retains only candidates supported by both the localized evidence and the authoritative MITRE definition. We contribute two evaluation resources--a cleaned TRAM benchmark (TRAM-Clean) and a new annotated dataset (TTPrint-Bench)--to address known annotation noise in existing benchmarks and elevate the task to document-level TTP extraction. On TRAM-Clean and TTPrint-Bench, TTPrint achieves 76.48% and 87.39% macro-F1 respectively, outperforming the leading baseline by 63.5% and 29.4%. A multi-backbone analysis across six LLMs and a threshold sensitivity study further demonstrate generalizability across model choices and provide practical guidance for parameter selection.

Yutong Cheng, Changze Li, Raihan Sultan Pasha Basuki +3

Virginia Tech · Universitas Ary Ginanjar, Jakarta, Indonesia · Amazon

Cyber Threat Intelligence Document Information Extraction Cybersecurity LLMs for Cybersecurity

May 25, 2026cs.CL

Double Triangle Annotation: A Scalable Human-in-the-Loop Framework for High-Precision Historical Document Annotation

Evaluating structured-information extraction from historical documents at scale requires high-precision ground-truth annotations, yet traditional manual labeling is expensive and fully automated pipelines built on large language models are prone to hallucination. We propose Double Triangle Annotation, a two-layer human-in-the-loop framework that leverages cross-model consensus to automate the majority of annotation work while ensuring high-precision outputs. In the first layer, two architecturally independent Multimodal Large Language Models annotate each document in parallel; when they agree, the label is auto-accepted, and disagreements are routed to a human jury. A second layer cross-checks two such systems against each other, escalating residual conflicts to a domain expert. The framework rests on a single assumption -- error independence between models -- requires no distributional priors or task-specific calibration, and becomes more autonomous as model capability improves. On the Guides Rosenwald, a corpus of French medical directories spanning 1887-1906, the framework achieves a final Word Error Rate of 0.003. Applied at scale, model consensus auto-accepts over 85% of 13,595 fields. We release the resulting benchmark -- the first structured-extraction ground truth for the Rosenwald Guides -- to support future work on historical document processing.

Yi Ren

École Polytechnique Fédérale de Lausanne

Historical Document Analysis LLM-Assisted Annotation Human-in-the-Loop Annotation Document Information Extraction Language Model Ensembles Historical Document Processing

May 24, 2026cs.AI

Noise-Robust Financial Numerical Entity Attribute Tagging

Financial Numerical Entity (FNE) understanding aims to recover the meaning of numerical mentions in financial reports. Existing studies primarily focus on concept name prediction and face two important limitations. First, labels derived from inline XBRL may contain errors because filings are usually prepared manually. Second, other important FNE attributes, such as reporting-time relation, measurement scale, and accounting sign, are less emphasized. We propose \textbf{NO}ise-\textbf{R}obust Tagging for Rich Financial Numerical Entity \textbf{A}ttributes (\textsc{NORA}) to address these gaps. NORA uses task-aware instance-specific weighting to attenuate the influence of noisy labels during training, and we further propose the Neighborhood Prior-adjusted KNN (NPK) filtering method for more reliable evaluation on real-world noisy test sets. In addition, we construct a large-scale benchmark containing 6.6 million instances with multi-attribute labels and filing metadata. Experiments show that \textsc{NORA} performs strongly compared with state-of-the-art noisy-label baselines, including Co-teaching, Mixup, SSR, and SelfMix. Moreover, NORA is robust under both unfiltered and noise-filtered test settings. It achieves the best Accuracy, Macro F1, and Weighted F1 for concept name and time-relation prediction, while remaining competitive on scale and sign prediction. These results demonstrate the value of jointly modeling rich FNE attributes while accounting for label noise in real-world financial filings.

Hsin-Min Lu, Chen-Yang Lai, Yi-Jhen Li +1

National Taiwan University · National Central University

Document Information Extraction Noisy-Label Learning Finance

May 22, 2026cs.CL

SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction

Joint Entity and Relation Extraction (JERE) is highly sensitive to training data quality, making data augmentation a natural way to improve generalization. However, existing augmentation methods often weaken entity relevance and disrupt semantic structure, limiting their effectiveness for JERE. In this paper, we propose \textbf{Structured Semantic Data Augmentation (SSDAU)}, a method designed to preserve triple-aware semantic structure during augmentation. SSDAU segments text by entity labels, captures semantic features through context-aware encoding, and restructures entity semantics to generate augmented data. To distinguish semantically similar entities, SSDAU combines contextualized embeddings with traditional similarity scores. To reduce topic inconsistency, we apply BERTopic-based filtering to remove irrelevant augmentations. We evaluate SSDAU on datasets with different annotation types and compare its performance on five representative JERE models against seven popular augmentation baselines. Experiments show that SSDAU generates semantically consistent data, is more robust to ambiguity than non-LLM methods (8.95% vs. 23.58% average relative F1 decrease), and significantly outperforms strong alternatives in most settings.

Jiawei He, Mengyu Shi, Jiawei Liu +6

State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China · Amap, Alibaba Group, China · University of Alberta, Edmonton, Canada +1

Relation Extraction Synthetic Data Augmentation Document Information Extraction

May 21, 2026cs.CV

From Recognition to Reasoning: Benchmarking and Enhancing MLLMs on Real-World Receipt Document Understanding

Extracting structured information from visual documents (Visual Information Extraction, VIE) is a cornerstone of business automation. While recent Multimodal Large Language Models (MLLMs) have shown promising capabilities, existing benchmarks suffer from critical limitations in scale and realism, lack semantic granularity, and fail to cover diverse document types. To bridge this gap, we introduce ReceiptBench, a large-scale, human-annotated benchmark consisting of 10k diverse receipts, organizing information extraction into four hierarchical sub-tasks: (1) Basic Perception for raw text spotting, (2) Format Normalization for strictly following standardization instructions, (3) Semantic Reasoning for inferring implicit attributes from context, and (4) Structure Parsing for handling nested line items. Furthermore, we propose a two-stage training framework incorporating Metric-Aware Group Relative Policy Optimization (GRPO), which translates rigorous evaluation constraints into reinforcement learning signals to enhance structural consistency. Extensive experiments demonstrate that our method yields state-of-the-art performance, surpassing leading proprietary models on complex reasoning tasks. We release our datasets and code at https://github.com/wwwT0ri/ReceiptBench.

Yandi Wang, Libin Zhan, Ziwei Huang +5

Zhejiang University, China

Document Understanding Document Information Extraction Multimodal Large Language Models

May 21, 2026cs.AI

Format-Constraint Coupling in Knowledge Graph Construction from Statistical Tables

An extraction schema should not reduce knowledge graph fidelity. On statistical CSV, however, it can. We study country-by-year time-series matrices, a common layout on open-data portals. In this setting, serialization format and schema constraints interact super-additively. Their joint effect exceeds the sum of independent effects by up to +1.180 (2x2 factorial, 6 datasets). Bootstrap 95% CIs are strictly positive on 4/6 datasets, with strongest evidence on wide Type-II matrices. More critically, a schema applied to a mismatched format can trigger catastrophic mismatch. Fact coverage falls below the unconstrained baseline on 4/6 datasets through entity inflation or extraction refusal. We call this observed pattern format-constraint coupling. Probing and token ablation support a surface-form anchoring explanation centred on column-name references. Controlled variants across format-schema pairings, GraphRAG hosts, and LLM families show the same direction within the measured scope; one LLM family shows only partial activation. The observation also has a diagnostic consequence. Three standard retrieval modes largely mask construction quality (delta <= 1pp), whereas direct graph access exposes gaps up to +47.6pp (p < 0.0001). To support fidelity-aware evaluation, we release CSVFidelity-Bench. It contains 15 datasets, 11 Type-II matrices, 4 Type-III tables, and 1,892 Gold Standard facts across 6 domains.

Jingxuan Qi, Zhiqiang Ye, Yuxiang Feng

South China University of Technology · Guangzhou, China

KG Construction Document Information Extraction Knowledge Graphs

May 20, 2026cs.CL

WCXB: A Multi-Type Web Content Extraction Benchmark

Web content extraction - isolating a page's main content from surrounding boilerplate - is a prerequisite for search indexing, retrieval-augmented generation, NLP dataset construction, and large language model training. Progress in this area has been constrained by the limitations of existing evaluation benchmarks, which are small (100-800 pages), restricted to news articles, or based on web pages from over a decade ago. We introduce the Web Content Extraction Benchmark (WCXB), a dataset of 2,008 web pages from 1,613 domains spanning seven structurally distinct page types: articles, forums, products, collections, listings, documentation, and service pages. The dataset includes a 1,497-page development set and a 511-page held-out test set with matched page type distributions. Ground truth annotations were produced through a five-stage pipeline: LLM-assisted drafting, automated verification, four-pass frontier model review, snippet and quality verification scripts, and human review. We evaluate 13 extraction systems - 11 heuristic and 2 neural - and find that while top systems converge on articles (F1 = 0.93), performance diverges sharply on structured page types (F1 = 0.41-0.84), revealing blind spots invisible to existing article-only benchmarks. The dataset is released under CC-BY-4.0 with HTML source files, ground truth annotations, page type labels, and baseline results.

Murrough Foley

Document Information Extraction

May 19, 2026cs.IR

Beyond Text and Tables: Vision-Language Model Integration in ComProScanner for Extracting Materials Data from Scientific Figures with High Accuracy

Automated extraction of materials composition-property data from scientific literature has advanced considerably with the development of large language model-based pipelines; however, existing frameworks remain limited to textual and tabular content, overlooking the substantial proportion of quantitative property data reported exclusively in scientific figures. Here, we extend ComProScanner, a fully end-to-end multi-agent framework for automated composition-property database construction, with a native vision-language model (VLM) based figure extraction capability. The extension introduces a FigureExtractor utility for caption-keyword-based figure filtering across all supported publishers, and a GraphExtractorTool agent that passes extracted figures to a configurable VLM to recover composition-property pairs from scientific charts and plots. Four VLMs are selected for evaluation on the basis of the LMArena Diagram leaderboard with an input cost criterion of less than $1.50 per million tokens. Benchmarking on 50 piezoelectric ceramic articles from the established

d_{33}

test corpus demonstrates that Gemini-3-Flash-Preview achieves the highest performance with a composition accuracy of 0.97 and a normalised F1 score of 0.97, whilst remaining the most cost-effective model among the four evaluated. We additionally introduce a range-based value error threshold parameter into the evaluation framework, providing a more physically meaningful assessment of numeric property values extracted from figures than exact value matching. These contributions establish VLM-integrated ComProScanner as the first materials-specific, fully automated, multimodal literature mining platform capable of extracting structured composition-property data from text, tables, and figures within a single unified pipeline.

Aritra Roy, Enrico Grisan, Chiara Gattinoni +1

Energy, Materials and Environment Research Centre, London South Bank University, London SE1 0AA, UK. · School of Engineering and Design, London South Bank University, London SE1 0AA, UK. · Bioscience and Bioengineering Research Centre, London South Bank University, London SE1 0AA, UK. +1

VLM Evaluation Document Information Extraction Chart Data Extraction Large Language Model-Guided Scientific Discovery

May 16, 2026cs.AI

MADP: A Multi-Agent Pipeline for Sustainable Document Processing with Human-in-the-Loop

Document processing automation remains a critical challenge in enterprise environments, where traditional manual approaches are labor-intensive and error-prone. We present MADP, a multi-agent architecture that addresses the challenge of automating document processing in enterprise settings by combining deep learning-based classification and parsing with large language model extraction, while maintaining accuracy through selective human validation. Our system integrates five specialized agents--Classificator, Splitter, Parser, Extraction, and Validator--with a Human-in-the-Loop (HITL) mechanism and a novel Prompt Fine Tuning with Feedback Inheritance (PFTFI) approach. The operational analysis on a production use-case scenario of 100,000 invoices per year indicates a potential reduction of Full-Time Equivalent (FTE) requirements by approximately 70%. Production deployment on 955 real-world documents processed through January 2026 achieves a 97.0% full-pipeline automation rate, with only 3% requiring non-AI fallback. Ablation evaluation on a stratified 100-document subset (5 documents per each of 20 supplier/document-type categories) demonstrates that the full MADP configuration with Human-in-the-Loop supervision attains 98.5% document-level accuracy. Additionally, we present a comprehensive sustainability analysis showing that our hybrid AI+HITL approach reduces CO2 emissions by 69%, energy consumption by 69%, and water usage by 63% compared to traditional manual processing. Benchmark comparisons of multiple LLM backends (Granite-Docling, Mistral-Small, DeepSeek-OCR) provide practical insights for deployment in production environments.

Diego Gosmar, Giovanni Zenezini

Tesisquare Head of AI, Turin, Italy · Polytechnic University of Turin, Department of Management and Production Engineering, Torino, Italy

Multi-Agent LLM Systems Document Information Extraction Human-in-the-Loop AI Workflow Automation

May 16, 2026cs.CL

RTI-Bench: A Structured Dataset for Indian Right-to-Information Decision Analysis

India's Right to Information Act, 2005 gives every citizen the right to demand information from public authorities, yet in practice most people cannot make sense of the dense administrative language used in Central Information Commission (CIC) decisions, let alone predict whether an appeal is worth filing. This paper introduces RTI-Bench, a structured dataset of CIC decisions with outcome labels, exemption citations, IRAC-style reasoning components, and procedural timelines. To the best of our knowledge it is the first publicly released structured dataset for Indian RTI administrative decisions. The dataset draws from two sources: 1,218 cases from a publicly available instruction-response corpus (with structured fields added through rule-based extraction), and 298 CIC decision PDFs collected directly from the Commission portal, spanning five commissioners and three document format generations from 2023 to 2026. Label coverage reaches 89% on the instruction-response corpus. For the PDF subset of 239 primary decisions, coverage is 51% in this first release. A random sample of 50 labelled cases was manually reviewed, yielding a label precision of 95.3%. A zero-shot Mistral 7B baseline on 100 cases gives 57.3% accuracy and 37.0% macro-F1 on outcome prediction, well above the majority-class baseline of 14.3% macro-F1. RTI-Bench is available at https://huggingface.co/datasets/joyboseroy/rti-bench

Joy Bose

Independent Researcher, Bengaluru, India

AI-Assisted Decision Making Legal Judgment Prediction Document Information Extraction

May 15, 2026cs.DL

paper.json: A Coordination Convention for LLM-Agent-Actionable Papers

LLM agents routinely serve as first (and sometimes only) readers of academic papers, skimming for sub-claims, extracting reproducibility steps, and generalizing scope. Standard prose papers produce recurring failures in this role: sub-claims that cannot be cited at sub-paper granularity, scope overextension beyond what the paper tests, and figure commands buried in codebases rather than the paper itself. We propose paper.json, a companion JSON file that travels with the PDF and addresses each failure with a lightweight convention: stable claim IDs (C1), an explicit does-not-claim list (C2), exact per-figure shell commands (C3), and stable definition IDs (C5). A fifth convention (C4) holds that minimum viable compliance, hand-written JSON alongside the PDF, is achievable in under an hour for a finished paper without touching the human-readable output. C1, C2, C3, and C5 are open invitations: an agent that reads a compliant paper and acts on it produces evidence for or against them. This paper is itself compliant: uv run validator.py paper.json --against paper.typ passes. Repo: https://github.com/arquicanedo/paper-json

Arquimedes Canedo

Document Information Extraction LLM Agents LLM Agent Reliability

May 15, 2026cs.CL

Ontology for Policing: Conceptual Knowledge Learning for Semantic Understanding and Reasoning in Law Enforcement Reports

Law enforcement reports contain structured fields and written narratives. However, many incident facts that are needed for review, police training, and investigations are in natural language and require manual reading. We propose a framework using symbolic methods for converting narratives into evidence-linked facts. Our objective is to measure the value of narratives to recover incident details only from the unstructured text and build temporal graphs with time cues and domain axioms. We achieve this by redacting personal identifiers, semantic parsing, predicate mapping to ontology, and reasoning. We evaluate the symbolic approach on 450 property crime reports and a short human review. Of the extracted events from the system, 54.1% had a confidence score of at least 0.80 and 93.7% were mapped through the PropBank--VerbNet--WordNet semantic path. 100% agreement was reached on incident initiation, stolen items, and temporal cues and lower agreement for forced entry interpretation.

Anita Srbinovska, Jansen Orfan, Adrian Martin +1

Office of Business Intelligence Rochester Police Department Rochester, NY, USA · Department of Computer Science Rochester Institute of Technology Rochester, NY, USA · School of Mathematics and Statistics Rochester Institute of Technology Rochester, NY, USA

KG Construction Document Information Extraction Semantic Mapping Temporal KGs

May 13, 2026cs.LG

LIFT: Last-Mile Fine-Tuning for Table Explicitation

We propose last-mile fine-tuning, or Lift, a pipeline in which a pre-trained large language model extracts an initial table from unstructured clipboard text, and a fine-tuned small language model (1B-24B parameters SLM) repairs errors in the extracted table. On a benchmark of 2,596 tables from three datasets, Lift matches or exceeds end-to-end SLM fine-tuning on tree-edit-distance-based similarity (TEDS) metric while requiring as little as 1,000 training examples - where it outperforms end-to-end fine-tuning by up to 0.144 TEDS points. We term this approach last-mile fine-tuning and show it also more robust to input format variability. Comparisons with self-debug and end-to-end fine-tuning approaches show that last-mile fine-tuning provides an attractive option when training data is limited or when robustness to input variation is sought without compromising on accuracy.

Divij Khaitan, Ashish Tiwari

Microsoft Corporation Bangalore, India · Microsoft Corporation Redmond, WA 98052 USA

Supervised Fine-Tuning Fine-Tuning LLM Fine-Tuning Document Information Extraction Language Model Robustness

May 12, 2026cs.AI

Operationalizing Document AI: A Microservice Architecture for OCR and LLM Pipelines in Production

Academic research tends to focus on new models for document understanding creating a wide gap in the literature between model definition and running models at production scale. To close that gap, we present a microservice architecture that encapsulates pipelines of multiple models for classification, optical character recognition (OCR), and large language model structured field extraction as well as our experience running this pipeline on thousands of multi-page documents per hour. We describe our primary design decisions, including a hybrid classification, separation of GPU-bound inference from CPU-bound orchestration, use of asynchronous processing for the many IO-bound operations in the pipeline, and an independent, horizontal scaling strategy. Using batch profiling, we identified two surprising qualitative findings that shape production deployments: OCR, not language-model parsing, dominates end-to-end latency, and the system saturates at a concurrency determined by shared GPU-inference capacity rather than worker count. Our goal is to provide practitioners with concrete architectural patterns for building document understanding systems that work beyond the benchmark; effectively operationalizing models in production.

Yao Fehlis, Benjamin Bengfort, Zhangzhang Si +9

Software Engineering Document Information Extraction Microservice Architecture Document Image Understanding

May 11, 2026q-bio.QM

Beyond Manual Curation: Augmenting Targeted Protein Degradation Databases via Agentic Literature Extraction Workflows

Predictive models in biomedicine depend on structured assay data locked in the text, tables, and supplements of primary publications. This bottleneck is especially acute in targeted protein degradation (TPD), where each assay record must combine compound identity, degradation target, recruiter, assay context, and endpoint values reported across sections, tables, and supplementary files. Inconsistent compound identifiers and incomplete or implicit assay context further demand domain-specific logic that generic LLM pipelines do not provide. Existing molecular glue and PROTAC databases are manually curated and often lack the experimental context required for downstream modeling. We formulate TPD database extraction as a domain-specific curation task and present an expert-in-the-loop LLM workflow, evaluated through a triangular comparison among LLM predictions, standardized baseline records, and expert-annotated ground truth. A lightweight cross-validated prompt-refinement module adapts extraction instructions from scarce expert annotations. With only seven annotated molecular glue publications, the workflow achieved record-level

F_1 = 0.98

and transferred to PROTACs by terminology substitution alone, maintaining record-level

F_1 > 0.93

. Applied at scale, it expanded molecular glue and PROTAC databases by 81% and 92% records, respectively, with 92% and 82.5% of newly recovered records validated as correct upon expert review. The workflow also recovered kinetic and assay-context information essential for cross-study potency comparison and condition-aware degradation modeling. We release the workflow, prompts, evaluation code, and extracted datasets as resources for TPD data curation and AI-assisted scientific curation more broadly.

Yaochen Rao, Farzaneh Jalalypour, N. M. Anoop Krishnan +1

Department of Computer Science and Engineering, Chalmers University of Technology and University of Gothenburg, Gothenburg, SE · Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi, New Delhi, IN

Training Data Curation Document Information Extraction LLM Information Extraction

May 11, 2026cs.SE

Read, Extract, Classify: A Tool for Smarter Requirements Engineering

This paper presents the ReXCL tool, which automates the extraction and classification processes in requirements engineering, enhancing the software development life-cycle. The tool features two main modules: Extraction, which processes raw requirement documents into a predefined schema using heuristics and predictive modeling, and Classification, which assigns class labels to requirements using adaptive fine-tuning of encoder-based models. The final output can be exported to external requirement engineering tools. Performance evaluations indicate that ReXCL significantly improves efficiency and accuracy in managing requirements, marking a novel approach to automating the schematization of semi-structured requirement documents.

Paheli Bhattacharya, Manojit Chakraborty, Santhosh Kumar Arumugam +1

Bosch Research and Technology Centre, Bangalore, India

Requirements Engineering Document Information Extraction Automated Software Engineering

May 11, 2026cs.CL

GLiNER-Relex: A Unified Framework for Joint Named Entity Recognition and Relation Extraction

Joint named entity recognition (NER) and relation extraction (RE) is a fundamental task in natural language processing for constructing knowledge graphs from unstructured text. While recent approaches treat NER and RE as separate tasks requiring distinct models, we introduce GLiNER-Relex, a unified architecture that extends the GLiNER framework to perform both entity recognition and relation extraction in a single model. Our approach leverages a shared bidirectional transformer encoder to jointly represent text, entity type labels, and relation type labels, enabling zero-shot extraction of arbitrary entity and relation types specified at inference time. GLiNER-Relex constructs entity pair representations from recognized spans and scores them against relation type embeddings using a dedicated relation scoring module. We evaluate our model on four standard relation extraction benchmarks: CoNLL04, DocRED, FewRel, and CrossRE, and demonstrate competitive performance against both specialized relation extraction models and large language models, while maintaining the computational efficiency characteristic of the GLiNER family. The model is released as an open-source Python package with a simple inference API that allows users to specify arbitrary entity and relation type labels at inference time and obtain both entities and relation triplets in a single call. All models and code are publicly available.

Ihor Stepanov, Oleksandr Lukashov, Mykhailo Shtopko +1

Knowledgator Engineering, Kyiv, Ukraine · Baldor Technologies Pvt. Ltd. (IDfy), Mumbai, India

Relation Extraction KG Construction Named Entity Recognition Document Information Extraction

May 11, 2026cs.CL

GLiNER2-PII: A Multilingual Model for Personally Identifiable Information Extraction

Reliable detection of personally identifiable information (PII) is increasingly important across modern data-processing systems, yet the task remains difficult: PII spans are heterogeneous, locale-dependent, context-sensitive, and often embedded in noisy or semi-structured documents. We present GLiNER2-PII, a small 0.3B-parameter model adapted from GLiNER2 and designed to recognize a broad taxonomy of 42 PII entity types at character-span resolution. Training such systems, however, is constrained by the scarcity of shareable annotated data and the privacy risks associated with collecting real PII at scale. To address this challenge, we construct a multilingual synthetic corpus of 4,910 annotated texts using a constraint-driven generation pipeline that produces diverse, realistic examples across languages, domains, formats, and entity distributions. On the challenging SPY benchmark, GLiNER2-PII achieves the highest span-level F1 among five compared systems, including OpenAI Privacy Filter and three GLiNER-based detectors. We publicly release the model on Hugging Face to support further research and practical deployment of open PII detection systems.

Urchade Zaratiana, Ash Lewis, George Hurn-Maloney

Fastino Labs

Named Entity Recognition Document Information Extraction PII Detection

May 10, 2026cs.CL

Key Coverage Matters: Semi-Structured Extraction of OCR Clinical Reports

Clinical reports are often fragmented across healthcare institutions because privacy regulations and data silos limit direct information sharing. When patients seek care at a different hospital, they often carry paper or scanned reports from prior visits. This hinders EHR integration and longitudinal review, and downstream applications that depend on more complete patient records, such as patient management, follow-up care, real-world studies, and clinical-trial matching. Although OCR can digitize such reports, reliable extraction remains challenging because clinical documents are heterogeneous, OCR text is noisy, and many healthcare settings require low-cost on-premise deployment. We formulate this problem as canonical key-conditioned extractive question answering over OCR-derived clinical reports. Because the key fields are neither fixed nor known in advance, the key space is open. We maintain a canonical key inventory through iterative key mining, normalization, clustering, and lightweight human verification, and introduce key coverage as a metric to quantify inventory completeness. Using a 0.2B BERT-based model, experiments on real-world reports from more than 20 hospitals show performance improves monotonically with key coverage. The model achieves F1 scores of 0.839 and 0.893 under exact match and boundary-tolerant matching, respectively, once the Top-90 canonical keys are covered. These results show that key coverage is a dominant factor for end-to-end performance. At Top-90 coverage, our model outperforms a fine-tuned Qwen3-0.6B baseline under exact match. Although our annotated corpus is Chinese, the method relies on the language-agnostic key-value organization of semi-structured clinical reports and can be adapted to other settings given an appropriate canonical key inventory and alias mapping.

Yu Wang, Yingyun Li, Ying Qin +1

AI Starfish, Hangzhou, China

Healthcare Document Information Extraction Clinical Information Extraction Clinical QA Electronic Health Records

May 8, 2026cs.CL

TCMIIES: A Browser-Based LLM-Powered Intelligent Information Extraction System for Academic Literature

The exponential growth of academic publications has created an urgent need for automated tools capable of extracting structured knowledge from unstructured scientific texts. While large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding and information extraction, existing solutions often require specialized infrastructure, programming expertise, or fine-tuned domain-specific models that create barriers for researchers in specialized fields. This paper presents TCMIIES, a browser-based, zero-installation platform that leverages commercial LLM APIs to perform structured information extraction from academic literature. The system employs a novel schema-guided prompting framework with automatic system prompt generation, enabling researchers to define custom extraction schemas through an intuitive graphical interface without any programming. TCMIIES features a pure front-end architecture that ensures data privacy by processing all information locally in the browser, supports five major LLM providers, implements concurrent batch processing with automatic retry mechanisms, and provides intelligent field mapping for Chinese academic databases including CNKI and Wanfang. We demonstrate the system's effectiveness through comprehensive evaluation across multiple extraction scenarios in Traditional Chinese Medicine research, achieving structured output compliance rates exceeding 94% and information extraction accuracy comparable to domain-expert annotation. The system represents a practical, accessible solution that bridges the gap between advanced LLM capabilities and domain-specific academic information extraction needs, particularly for researchers in specialized fields who require flexible, privacy-preserving, and cost-effective extraction tools.

Hanqing Zhao

Hebei University, College of Traditional Chinese Medicine Baoding, Hebei 071002, China

Document Information Extraction LLM Information Extraction

May 7, 2026cs.AI

Systematic Evaluation of Large Language Models for Post-Discharge Clinical Action Extraction

The work in this paper evaluates zero-shot and few-shot large language models (LLMs) for safety-critical clinical action extraction using the CLIP discharge-note dataset, with particular emphasis on transitions of care and post-discharge patient safety. To manage the complexity of clinical documentation, we introduce a two-stage extraction framework that decomposes discharge notes, that are written in narrative form, into fine-grained, explicitly actionable clinical tasks through a staged prompting strategy. Our contributions include a systematic assessment of generative LLMs for clinical action extraction, a detailed comparison between general-purpose LLMs and task-specific supervised BERT-based models, and an analysis of annotation inconsistencies across different action categories. We show that contemporary LLMs achieve performance comparable to or exceeding supervised models on binary actionability detection, while supervised baselines retain a meaningful advantage on fine-grained multi-label category classification, despite the absence of task-specific fine-tuning and under strict data-privacy constraints. Qualitative error analysis reveals that many failures stem from misalignment between model reasoning and dataset annotation conventions, particularly in cases involving implicit clinical actions and rigid structural labeling rules. These results indicate that reported performance reflects model limitations due to lack of clinical reasoning, that is not captured by plain annotations. Labels without rationales make it impossible to distinguish clinical reasoning failures from annotation convention mismatches. Advancing clinical NLP requires reasoning-annotated datasets that document why specific spans are actionable, not merely which spans were labeled, enabling proper evaluation of model clinical understanding.

Shivali Dalmia, Ananya Mantravadi, Prasanna Desikan

Centific AI Research · Centific Global Solutions, Inc.

Document Information Extraction Clinical Information Extraction LLM Information Extraction Clinical Language Model Evaluation