scientific information extraction

To address the error-prone and inefficient manual rewriting of data transformation logic upon JSON Schema evolution, this paper proposes a type-directed, top-down program synthesis approach for automatically generating semantics-preserving JSON Schema converters. Our method integrates type inference, semantic constraint modeling, a rewrite system, and intermediate representation (IR)-driven code generation to guarantee lossless data transformation and formal verifiability. It natively supports complex nested schemas and synthesizes correct, efficient, and human-readable Python and JavaScript conversion code. We evaluate our approach on real-world API configuration schemas and healthcare data integration scenarios, demonstrating its safety—via formal guarantees and empirical validation—its practical utility in industrial settings, and its generalizability across diverse schema evolution patterns. Experimental results confirm high accuracy, robustness to structural changes (e.g., field additions, type refinements, nested object restructuring), and scalability to large, deeply nested schemas.

The explosive growth of scientific literature poses significant challenges for interdisciplinary knowledge integration. Method: This paper proposes a lightweight, LLM-driven approach to structured knowledge construction, integrating large language models with a reusable scientific concept ontology—avoiding costly retrieval-augmented generation or opaque semantic modeling. Using only 20 annotated abstracts, the method achieves cross-domain generalization of scientific concepts; it introduces a lightweight, interdisciplinary-compatible ontology schema ensuring interpretability and extensibility; and constructs a domain-spanning knowledge graph covering astrophysics, fluid dynamics, and evolutionary biology, scaled to 30,000 arXiv papers. Contribution/Results: The resulting system enables precise literature question answering and scientific trend analysis. All components—including the ontology, annotation guidelines, and graph construction pipeline—are fully open-sourced to support reproducible, transparent scholarly analysis.

Scientific process descriptions are often embedded in unstructured text, hindering reproducibility, comparison, and automation. To address this challenge, this work presents the first cross-disciplinary, expert-driven repository of structured scientific process schemas, encompassing 16 expert-annotated patterns across five domains. Through a human-in-the-loop workflow, candidate schemas generated by large language models were iteratively refined via domain expert feedback, yielding reusable fields such as inputs, outputs, steps, and parameters. The resulting schemas are formalized in both JSON Schema and SHACL formats and accompanied by an integrated toolchain. The project also releases a comprehensive dataset—including schemas, intermediate artifacts, review records, and analysis scripts—to support knowledge graph construction, semantic publishing, and cross-study comparison.

Current structured data modeling and cross-format schema mapping lack accessible, low-threshold tools—particularly hindering non-expert users. This paper proposes a hybrid approach synergizing large language models (LLMs) with deterministic rule-based processing: LLMs interpret natural-language requirements to generate or refine JSON Schema, while a verifiable rule engine performs high-precision, scalable schema mapping across multiple formats (JSON, CSV, XML, YAML). The method is implemented in the open-source tool MetaConfigurator, supporting visual schema modeling and automated code generation. Empirical evaluation in the chemistry domain demonstrates substantial reductions in modeling barriers, significant improvements in schema construction efficiency and mapping accuracy, and—critically—the first end-to-end data schema engineering solution that is natural-language-driven, flexible, and formally reliable.

This work addresses high-accuracy conversion of unstructured/semi-structured documents (e.g., contracts, academic papers, invoices) into structured, machine-readable data. Method: We systematically survey and empirically compare modular pipeline approaches against end-to-end multimodal large models, proposing a unified framework integrating OCR, layout analysis (LayoutParser), graph neural networks, vision-language models (VLMs), and specialized formula/table recognition. We identify and characterize core bottlenecks—layout understanding, dense text recognition, and cross-modal alignment—for the first time. Contribution/Results: We establish a comprehensive analytical framework covering methodology, challenges, and benchmarks, revealing >32% performance gaps of current SOTA on complex layouts (e.g., multi-column, nested tables). We propose a “dual-driven” evolution path emphasizing both data diversity and scale, and open-source a larger annotated dataset to significantly advance knowledge base construction and training-data generation for large models.

This work addresses the absence of an end-to-end evaluation benchmark and semantics-aware assessment framework for structured information extraction from PDFs under enterprise-grade, complex JSON schemas. We introduce ExtractBench, the first open-source benchmark comprising 35 high-value economic-domain PDF documents, human-annotated JSON schemas, and 12,867 evaluable fields. It features a novel fine-grained evaluation framework that treats JSON schemas as executable specifications, enabling field-level differentiated scoring—including exact match, tolerance-based, and semantic equivalence—and explicitly distinguishing omissions from hallucinations. Experiments on leading large language models (e.g., GPT-5/5.2, Gemini-3, Claude 4.5) reveal significant performance degradation in broad-schema scenarios, with effective output rates dropping to 0% on a 369-field financial statement schema, underscoring the current models’ severe unreliability in complex structured extraction tasks.

This work addresses the challenge that domain experts face in translating natural language descriptions of data quality requirements into executable analyses, a process often hindered by reliance on data engineers, resulting in inefficiency and high technical barriers. To overcome this, the paper proposes a no-code, model-driven pipeline that leverages a QPM metamodel to define domain-specific quality analysis templates. Coupled with the Constrainify toolchain, it automatically transforms natural language requirements into executable and reusable analytical logic. By integrating model-driven engineering, metamodeling, and no-code web technologies, the approach significantly reduces dependency on technical expertise, enabling efficient, reproducible, and semantically aligned data quality assessments. This advancement enhances both the accessibility and automation of data quality analysis for non-technical domain practitioners.

This study addresses the lack of efficient, automated methods for structuring heterogeneous real estate questionnaire documents. To this end, the authors propose an end-to-end information extraction framework that first categorizes documents into structural types using K-Means clustering and text classification. Subsequently, it leverages the DeepSeek-R1 large language model enhanced with prompt engineering to accurately extract 35 predefined attributes from complex document formats—including checkboxes and scanned images—and outputs them as structured JSON. Evaluated on a dataset of 2,781 documents, the method produced 2,766 unique property records. Downstream validation demonstrated a Jaccard similarity of 0.82, marking the first high-precision, scalable solution for structured information extraction from such challenging real estate documentation.

This work addresses the challenge of efficiently and accurately extracting complex nested structures from unstructured text and enabling semantic-level automated evaluation. The authors propose a schema-guided, end-to-end framework that integrates domain-specific knowledge schemas with generative AI models—such as Claude Opus 3—to perform zero-shot, one-pass extraction of hierarchical attributes with variable cardinality. Automated evaluation is achieved through path alignment and fine-grained semantic matching algorithms. The framework demonstrates strong transferability across models, institutions, and languages, successfully extracting 12 out of 14 attributes in NICE documents with F1 scores exceeding 90%. It achieves a 30-fold speedup over manual annotation while significantly improving extraction efficiency, consistency, and generalizability.

This work addresses the challenge of generating semantically accurate scientific architecture diagrams from natural language, a task hindered by the absence of high-quality, large-scale open datasets. To bridge this gap, the authors introduce the first large-scale open-source dataset specifically designed for this purpose, comprising scientific architecture diagrams, their corresponding textual descriptions, and associated DOT code representations. Leveraging this dataset, they fine-tune compact language models or employ GPT-4o with in-context learning to achieve high-fidelity text-to-diagram generation. Experimental results demonstrate that the fine-tuned small models match the performance of GPT-4o and significantly outperform baseline approaches such as DiagramAgent. The code, dataset, and trained models are publicly released to facilitate further research.