knowledge graphs and knowledge bases

To address the low efficiency of code understanding and file localization in large-scale software repositories, this paper proposes a graph-augmented hybrid retrieval framework. First, it leverages large language models (LLMs) to extract semantic summaries and generate fine-grained vector embeddings, while integrating static analysis to construct a knowledge graph encoding syntactic–semantic relationships—including inheritance, method calls, and references. Second, it introduces a graph-aware retrieval expansion mechanism that jointly optimizes semantic similarity matching and subgraph traversal, supporting LLM-generated constrained natural language queries and interpretable reasoning. Experimental results demonstrate significant improvements in accuracy and robustness for problem-driven file retrieval across multiple open-source projects. The approach achieves a substantial leap in automated code understanding capability and establishes a scalable, knowledge-infused infrastructure for intelligent development toolchains.

In the era of large language models, traditional record-centric data engineering struggles to meet the demand for organizational knowledge as executable infrastructure. This work proposes a novel paradigm—knowledge architecture—that systematically reimagines core data engineering mechanisms by upgrading ETL, data lineage, and catalogs into knowledge ingestion, change detection, provenance, and knowledge catalogs. It introduces knowledge views and a three-tier layered model (raw–refined–operational) to structure knowledge effectively. By integrating emerging standards such as LLM Wiki and Open Knowledge Format (OKF), this study formally defines knowledge architecture for the first time and establishes a theoretical framework that supports knowledge representation, governance, and operational delivery, enabling direct invocation of organizational knowledge by humans, agents, workflows, and models alike.

This work addresses the challenge of integrating and retrieving multi-source heterogeneous data arising from schema inconsistencies by proposing an “executable schema contract” mechanism. This approach enables structure-aware automatic knowledge graph construction through a combination of closed-world field catalogs, deterministic structural analysis (e.g., primary/foreign key detection and source hierarchy identification), and monotonic extension protocols. It integrates large language model–constrained schema discovery, schema-guided information extraction and deduplication, and a multi-tool agent routing strategy that supports structured queries, graph traversal, and vector search. Evaluated on four question-answering benchmarks, the method achieves significantly superior zero-shot performance compared to pure retrieval and decomposition-based baselines. Ablation studies confirm that schema-conditioned routing, structural reasoning, and schema-guided construction are critical to its performance gains.

To address the high barrier to FAIR knowledge graph (KG) construction caused by domain experts’ limited semantic modeling capabilities, this paper proposes Rosetta Statement—a lightweight metamodeling approach that uses natural-language sentences as atomic modeling units, decoupling semantic modeling from ontology engineering. It supports sentence-pattern versioning, dynamic natural-language rendering and editing, and traceable provenance, enabling ontology-agnostic schema definition on the Open Research Knowledge Graph (ORKG) platform. Innovatively integrating Wikidata term mapping, sentence-pattern metamodeling, and dynamic label generation, Rosetta Statement is extended with LLM support for sentence-driven data entry, visualization, and SPARQL/Cypher-free querying. Empirical validation on ORKG demonstrates that domain experts can independently author structured schemas, enabling a three-phase KG construction workflow and significantly improving modeling efficiency, cognitive interoperability, and FAIR compliance—establishing a low-barrier, high-usability KG construction paradigm.

This study addresses the fragmentation of research software and its associated scholarly resources—such as publications and datasets—across disparate platforms, which hinders reproducibility and cross-domain analysis due to a lack of unified semantic links. To bridge this gap, the authors construct a large-scale RDF knowledge graph comprising 81 million triples, integrating approximately 200,000 GitHub repositories with external academic knowledge graphs including SemOpenAlex, LPWC, and MLSea-KG. This integration enables unified semantic modeling of software alongside scholarly entities such as authors, papers, and datasets. The resulting knowledge graph supports cross-platform provenance tracing and complex semantic queries, significantly enhancing the capacity to assess software reproducibility and analyze its long-term sustainability within the scientific ecosystem.

This work addresses the challenge of inefficient cross-version querying in multi-version knowledge graphs under concurrent environments. The authors propose QuaQue, a system that enables efficient querying by translating SPARQL queries into SQL and leveraging a novel condensed algebra combined with a bitstring-encoded version storage mechanism within standard relational databases. This approach constitutes the first SPARQL-to-SQL translation framework that natively supports version semantics, significantly enhancing query performance through relational modeling of knowledge graphs. Experimental results demonstrate that QuaQue outperforms native RDF triplestore systems on standard benchmarks, establishing a new baseline for scalable and efficient versioned knowledge graph querying.

This work addresses the limitations of traditional knowledge graph construction approaches, wherein structural decisions are hard-coded into rigid pipelines, resulting in tight coupling between schema and construction process and hindering support for ontology-level tasks. To overcome this, the authors propose an ontology-oriented construction framework featuring a novel intrinsic-relational routing mechanism. This mechanism dynamically assigns attributes to corresponding schema modules through iterative attribute classification, enabling a declarative and reusable decoupled design. The pipeline integrates rule-based cleaning, tool-augmented large language model–assisted annotation, and human review. Evaluated on Wikidata (January 2026), the resulting graph comprises 34 million nodes and 61.2 million edges, achieving 93.3% schema coverage and 98.0% module assignment accuracy, effectively supporting five ontology-level applications.

Existing large language model–driven approaches to knowledge graph construction typically rely on stateless batch processing, which struggles to model cross-document semantic relationships, achieve precise entity disambiguation, and provide sufficient interpretability—limitations that hinder their deployment in high-stakes scenarios. To address these challenges, this work proposes the RAGA framework, which enables autonomous, end-to-end knowledge graph construction through a cognitive constraint mechanism of Read-Search-Verify-Construct and an atomic CRUD toolset. RAGA innovatively integrates ReAct-style agents, hybrid symbolic-vector retrieval, synchronized knowledge graph–vector updates, and evidence-anchored verification to substantially enhance the interpretability and traceability of the construction process. Evaluated on the QASPER scientific question answering subset, the method outperforms zero-shot baselines, significantly improving both answer accuracy and evidence quality.

This work addresses the common challenge faced by data analysts who begin with vague questions and iteratively refine their information needs through exploration. To support this process, the authors propose Pneuma-Seeker, a novel system that leverages large language models (LLMs) not as opaque question-answering engines but as transparent, interactive analytical collaborators. Pneuma-Seeker enables users to explicitly articulate their information requirements as verifiable relational specifications and supports iterative refinement of these specifications, targeted data discovery, and execution with full provenance tracking. By integrating LLMs with relational specification modeling, data provenance, and an interactive interface, the system demonstrates its effectiveness in two real-world public procurement use cases, where it successfully helped users dynamically concretize evolving analytical needs and accurately retrieve relevant data.

This study addresses the challenges of internal consistency and external interoperability in the automatic alignment and integration of heterogeneous knowledge graphs by proposing an ontology-compatible knowledge graph construction approach. The method integrates a novel ontology-driven term-matching algorithm, a schema-based compliance modeling mechanism, and a quantitative metric for assessing conformance, ensuring that the resulting knowledge graphs strictly adhere to prescribed ontological specifications at both structural and semantic levels. Experimental validation in the architectural domain demonstrates the effectiveness of the approach, significantly enhancing the interpretability of the knowledge graphs and their interoperability across systems. This work thus offers a viable pathway toward the automated fusion of heterogeneous knowledge graphs while preserving ontological fidelity.