Knowledge Graphs (KGs) are increasingly constructed through automated extraction pipelines; however, such systems often introduce spurious or incomplete triples, which degrade downstream performance. Existing evaluation practices rely heavily on task-specific metrics or small-scale manual verification, offering limited insight into the structural and semantic fidelity of extracted graphs.
arXiv:2607. 10212v1 Announce Type: new Abstract: Knowledge Graphs (KGs) are increasingly constructed through automated extraction pipelines; however, such systems often introduce spurious or incomplete triples, which degrade downstream performance.
arXiv:2606. 29180v1 Announce Type: new Abstract: A Knowledge Graph (KG) represents facts as structured triples and is widely used to organize relational knowledge across diverse domains.
The paper investigates whether large language models (LLMs) can construct knowledge graphs (KGs) from documents in a zero‑shot, schema‑free manner. It introduces the Detail‑to‑Abstract Hierarchical Knowledge Graph (D2A‑HKG) framework, which splits KG construction into extraction, splitting, and abstraction stages, and evaluates the resulting graphs semantically and structurally. Using seven leading LLMs, the authors benchmark zero‑shot KG construction on CMW‑Lit—a dataset of pediatric mental‑wellness research—and find that state‑of‑the‑art LLMs generally produce relevant, document‑faithful triples with limited hallucination, though their extraction behaviors vary across stages. The study releases CMW‑Lit and the generated graphs as resources for future research and downstream knowledge‑intensive applications.
arXiv:2609.09004v1 Announce Type: cross Abstract: Large Language Models (LLMs) demonstrate impressive performance across diverse NLP tasks, yet their ability to exhibit genuine contextual understandi...
arXiv:2510. 06039v2 Announce Type: replace-cross Abstract: Reliable evaluation of knowledge-grounded Large Language Models (LLMs) in Chinese requires resources that explicitly align Chinese-language text with verifiable Knowledge Graph (KG) facts.
arXiv:2607. 03447v1 Announce Type: cross Abstract: Knowledge graphs (KGs) that underpin Graph-based Retrieval-Augmented Generation (Graph-RAG) are increasingly built automatically by LLM-driven extraction rather than curated by experts.
arXiv:2601.10485v5 Announce Type: replace Abstract: Domain-specific knowledge graphs (DKGs) are critical yet often suffer from limited coverage compared to General Knowledge Graphs (GKGs). Existing t...
arXiv:2607. 28662v1 Announce Type: new Abstract: Large language models extract entities and relationships from unstructured documents fluently but inconsistently: type vocabularies fracture across documents, the same person surfaces under several name variants, relationships duplicate, and distinct individuals who share a name risk silent conflation.
arXiv:2604. 03496v2 Announce Type: replace Abstract: Knowledge graph generation typically relies either on predefined ontologies or on schema-free extraction.
The paper introduces a knowledge‑graph‑based evaluation framework, S3KG, to assess whether large language models truly understand context in question answering tasks. S3KG combines structural and semantic signals into a single similarity score and is paired with a diagnostic analysis that pinpoints reasoning errors at the triplet level. Across nine benchmarks, the method outperforms existing baselines, achieving up to +7.6 F1 points and an AUROC of 0.973.
arXiv:2508. 10971v2 Announce Type: replace-cross Abstract: Knowledge graphs (KGs) can be enhanced through rule mining; however, the resulting logical rules are often difficult for humans to interpret due to their inherent complexity and the idiosyncratic labeling conventions of individual KGs.
The paper introduces GONE, a benchmark for evaluating knowledge unlearning in large language models using structured knowledge graphs, and presents Neighborhood-Expanded Distribution Shaping (NEDS), a framework that leverages graph connectivity to separate forgotten facts from their semantic neighborhood. GONE disentangles direct fact removal, reasoning-based leakage, and catastrophic forgetting, while NEDS achieves high unlearning efficacy and locality on LLaMA-3-8B and Mistral-7B. The dataset is publicly available on Hugging Face.