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: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.
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:2606. 09105v1 Announce Type: new Abstract: Generating novel, feasible, and high-quality research ideas is an important yet challenging task in scientific discovery.
arXiv:2606. 19351v1 Announce Type: cross Abstract: Knowledge graph (KG) reasoning infers new knowledge from existing facts and is widely applied in question answering, recommendation, and decision support.
arXiv:2511.04473v3 Announce Type: replace Abstract: Retrieval of information from graph-structured knowledge bases represents a promising direction for improving the factuality of LLMs. While various...
arXiv:2603.28773v2 Announce Type: replace-cross Abstract: Large language models (LLMs) frequently generate confident yet factually incorrect content when used for language generation (a phenomenon of...
The paper evaluates recent large language models (LLMs) for knowledge graph-to-text generation against traditional fine‑tuned encoder‑decoder models. Using both reference‑based metrics and graph‑grounded, reference‑free LLM‑based evaluation, the authors find that LLMs close the performance gap on reference metrics and outperform fine‑tuned models on graph‑grounded metrics. The study also shows that LLM‑based evaluation scores correlate poorly with reference metrics, indicating they assess different aspects of quality, and that prompted LLMs produce fewer contradictions and omissions, especially as graph size increases.
arXiv:2608. 07023v1 Announce Type: cross Abstract: Organizing thousands of unstandardized, multilingual expertise declarations is a persistent challenge for Human Resources (HR) platforms, directly impacting downstream tasks like accurate talent matching.
The paper evaluates recent large language models (LLMs) for knowledge graph‑to‑text generation against traditional fine‑tuned encoder‑decoder models. Using both reference‑based metrics and graph‑grounded, reference‑free LLM‑based evaluation, the study finds that LLMs largely close the performance gap on reference metrics and outperform fine‑tuned models on graph‑grounded metrics. The results also show that LLM‑based evaluation correlates weakly with reference metrics, indicating that each captures distinct aspects of generation quality, and that prompted LLMs produce fewer contradictions and omissions, especially as graph size grows.
The paper presents an end‑to‑end pipeline for automatically constructing a tree‑structured knowledge graph (KG) from Vietnamese high school history textbooks and evaluating retrieval strategies that exploit the KG’s hierarchical structure. The KG construction uses a three‑phase hybrid relation extraction process, including intra‑batch deduplication, approximate cross‑batch search, and LLM extraction with a centroid filter and dual‑LLM validator, resulting in 750 nodes and 4,341 semantic edges across 41 ontology types. Retrieval evaluation compares three graph traversal strategies—Top‑Down, Horizontal, and Bottom‑Up—on a benchmark of 1,210 Vietnamese queries, finding that the Top‑Down strategy with structural information outperforms a vector baseline by 4.7 percentage points in NDCG@10.
arXiv:2606. 18075v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has emerged as a paradigm for enhancing large language models (LLMs) with external knowledge, yet existing graph-based methods face a fundamental limitation: entity-centric and chunk-centric approaches operate on representations anchored to original text without true knowledge fusion.
ConvergeWriter introduces a bottom‑up, data‑driven framework for long‑form document generation that first retrieves exhaustive knowledge from a source corpus and clusters it into distinct knowledge groups. These clusters then guide the creation of a hierarchical outline and the final text, ensuring the output is strictly grounded in the retrieved material and traceable to its sources. Experiments on 14B and 32B LLMs show that this approach matches or surpasses state‑of‑the‑art baselines, especially in scenarios requiring high factual fidelity and structural coherence.