Document-level relation extraction (DocRE) aims to extract relations among multiple entities across extended contexts while maintaining consistency across predicted triples. Although large language models (LLMs) show remarkable reasoning capabilities in information extraction, their predictions are typically generated independently for each candidate triple and may violate fundamental relational constraints such as transitivity, symmetry, and functional uniqueness, leading to contradictory and unreliable outputs. We propose CONSISTRE, a unified consistency-aware framework for DocRE that addresses this limitation through two complementary tracks. The first operates at inference time for black-box LLMs, combining constraint-aware prompting, constraint-based verification, and iterative self-reflection to refine predictions without task-specific fine-tuning. The second injects consistency knowledge into smaller open-source models via a knowledge distillation and reinforcement learning pipeline: reasoning traces from a powerful teacher are distilled into a student via supervised fine-tuning, followed by GRPO alignment using a composite reward that jointly optimizes extraction performance and relational consistency. Together, the two tracks cover both API-accessible and locally deployable scenarios under a unified consistency formulation. Experiments on DocRED show that both tracks outperform their baselines, with the inference-time track achieving competitive F1 using off-the-shelf black-box LLMs and the training-time track substantially narrowing the gap between 7--8B open-source models and state-of-the-art proprietary LLMs at a fraction of their inference cost. Ablation studies confirm that explicit consistency modeling mitigates relational contradictions and enhances the reliability of LLM-based DocRE across both deployment paradigms.
Large Language Models (LLMs) show considerable potential for materials-science question answering. However, LLM responses may still be affected by unsupported parametric associations, while dense Retrieval-Augmented Generation (RAG) can fragment relational evidence across text chunks. Moreover, general graph-based retrieval does not necessarily preserve the hierarchical relations and factual attributes required to resolve implicit material constraints. To address these limitations, we propose MCTD-KG, a multi-source heterogeneous knowledge graph integrated with a Knowledge-Enhanced RAG framework for complex material question answering. MCTD-KG adopts a Classification–Term–Data ontology to connect disciplinary taxonomies, domain concepts, semantic relations, and empirical records from toolbooks and the scientific literature. Through LLM-assisted knowledge extraction, entity normalization, and multi-source integration, the resulting graph contains more than 530,000 entities across three layers, including 61,768 text-extracted Term-layer entities. During inference, Dual-Channel Retrieval jointly retrieves query-relevant relational paths and associated material attributes, while an explicit semantic filtering stage screens candidate evidence against the query constraints. Evaluation on an expert-validated benchmark of 1577 questions shows that the proposed framework achieves an overall accuracy of 68.48%, compared with 17.40% for the zero-shot Pure LLM, 24.79% for the best Vanilla RAG setting, and 44.96% for GraphRAG. It also achieves 45.22% accuracy on four-hop questions, compared with 39.49% for GraphRAG. These results indicate that integrating multi-source domain knowledge with relation-preserved retrieval and attribute-supported filtering provides more focused and inspectable evidence, thereby supporting more accurate complex material question answering.
Peize Li, Xi Guo, Nan Yin et al.· Electronics· 0 citations
Extensive experiments demonstrate that AgentsKG outperforms state-of-the-art training-free baselines in both extraction accuracy and structural quality, offering a robust approach to open-domain knowledge graph construction without additional training.
Shilong Liu, Yongqiang Liu, Jiye Liu et al.· Proceedings of the 32nd ACM...· 0 citations
Knowledge Graph Question Answering has increasingly adopted a retrieval-reasoning decoupling paradigm, where large language models synthesize answers based on retrieved evidence subgraphs. However, existing retrieval methods often fail to jointly optimize semantic relevance and structural dependencies, resulting in fragmented evidence or search space explosion in multi-hop reasoning. In this work, we propose DuoFlow-KG, a unified dual-modal evidence retrieval framework that constructs compact, high-density evidence subgraphs through integrated structure-semantic modeling. Specifically, we introduce a dual-directional knowledge anchoring strategy that enriches entity representations by incorporating both incoming and outgoing relational neighborhoods with explicit inverse relation injection. A dual-modal fusion module is designed to project semantic resonance and topological distribution into a unified high-dimensional embedding space, where a scalar diffusion mechanism generates structural fingerprints to discriminate textually similar facts based on spatial reachability. Furthermore, we employ a hierarchical weak-supervision scheme, where diversity-aware sampling guided by Maximal Marginal Relevance is used to reduce redundancy and retain reasoning-critical evidence. Extensive experiments on WebQuestionsSP and ComplexWebQuestions benchmarks demonstrate that DuoFlow-KG achieves strong overall performance and best F1, achieving F1 scores of 77.28% and 61.33% respectively. Ablation studies confirm the complementary contributions of semantic modeling, structural reasoning, and bidirectional anchoring, particularly in complex multi-hop scenarios.
Liwei Wang, Zhijun Xie, Rui Wang et al.· Scientific Reports· 0 citations
Translating natural language into graph query languages (NL2GQL) enables non-expert users to access graph databases, but supervised parsers depend on large annotated corpora and costly retraining whenever the schema evolves. Few-shot in-context learning offers a training-free alternative, yet its effectiveness hinges on demonstration selection, and conventional retrieval based on sentence-level matching and a single similarity signal often overlooks beneficial exemplars. We propose MGDR-SDR, a training-free approach that applies constituency parsing to derive three complementary representations of the utterance: a shallow abstraction preserving fine-grained lexical and syntactic detail, a deep abstraction exposing the intent-level syntactic skeleton, and a noun phrase list capturing concrete graph elements. These representations drive a multi-granular retrieval procedure that aggregates evidence across dense and sparse channels, yielding broader and more precise demonstration coverage. We evaluate MGDR-SDR on SPARQL generation over KQA Pro and Cypher generation over ZOGRASCOPE. Without any training, it reaches 86.58% Hits@1 on KQA Pro, surpassing strong supervised parsers and setting a new state-of-the-art among few-shot methods, and it transfers across GQL formalisms, attaining the best iid accuracy and a balanced generalization profile that surpasses all open-source few-shot baselines on ZOGRASCOPE. These results show that syntax-derived, multi-granular retrieval is an effective and generalizable strategy for few-shot NL2GQL semantic parsing.
Tong Li, Zhipeng Du, Xinyu Hu et al.· Machine Learning and Knowled...· 0 citations
The results indicate that the proposed framework effectively enhances the quality and structural consistency of generated hyper-relational data while mitigating the effects of long-tail distributions and pseudo-negative samples without requiring additional manual annotations.
Xinzhi Du, Yan Chen, Siqi Xu et al.· Applied Sciences· 0 citations
General-purpose NLP embedding models perform well on linguistic tasks, but their ability to capture symbolic ontological structure remains unclear. We introduce AVA, a systematic framework for evaluating whether embeddings distinguish logic-sensitive relational semantics in ontologies and knowledge graphs. AVA comprises 171,007 contrastive triplets derived from 163 heterogeneous ontologies using hierarchy inversion, relation substitution, and disjointness injection. Each triplet contains an ontology statement, a semantically equivalent paraphrase, and a logic-sensitive hard negative with contradictory relational meaning. We evaluate more than 25 state-of-the-art embedding models and find substantial limitations: the best model achieves only 0.739 triplet accuracy, while hard negative accuracy falls to 0.135. Fine-tuning improves discrimination by a large margin but transfers poorly to downstream Semantic Web tasks, including taxonomy discovery and ontology alignment. Further analysis suggests that improvements stem partly from perturbation-specific pattern recognition rather than robust ontological understanding. These findings reveal a persistent gap between linguistic representation learning and ontology-level discrimination, challenging the assumption that strong NLP benchmark performance translates to Semantic Web competence.
Hamed Babaei Giglou, Jennifer D’Souza, S. Auer· 0 citations