HRE-LSC: A Hyper-Relational Data Enhancement Framework for Long Tail Distribution and Structural Consistency

CONSISTRE: A Unified Consistency-Aware Framework for Document-Level Relation Extraction with Large Language Models

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.

Improving large-scale DLA datasets through semantic validation and relation-aware multimodal LLMs

Towards Building a Multi-Source Heterogeneous Knowledge Graph for Complex Material Question Answering

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.

ZeroRel: Relational Reasoning via Graph-guided Large Language Models

Relational databases (RDBs) play an essential role in real-world scenarios, such as e-commerce, social media, and industry. Recently, with the rapid development of Large Language Models (LLMs), using LLMs to exploit RDBs has become a significant trend. Plenty of works have been proposed to use natural language to describe RDBs or use graph neural networks~(GNNs) to embed relations in RDBs before applying LLMs to them. Despite the achieved progress, existing works still suffer from inevitable weaknesses. For one thing, using natural language to describe RDBs not only causes excessive context length, but also leads to the loss of critical structural information. For another, using GNNs to capture complex structural dependencies requires extensive human-labeled data for supervised fine-tuning, limiting their scalability. Therefore, one important question remains unsolved: '' How to leverage the capability of LLMs to realize robust relational reasoning in RDBs? '' In response, we propose a novel self-supervised framework (ZeroRel) for relational reasoning over RDBs. ZeroRel treats context sparsity as a controllable curriculum variable and leverages it to induce a progressive shift from semantic-dominant inference to structure-aware relational reasoning. Specifically, ZeroRel contains two key modules: Graph-guided Prompt Alignment (GrPA) and Progressive Sparsity-based Context Refinement (PSCR). GrPA uses a heterogeneous GNN to encode multi-table relational structures and projects the resulting structural embeddings into the semantic space of LLMs. PSCR gradually reduces visible attribute context and acts as an information bottleneck, forcing the model to internalize cross-table dependencies rather than relying on superficial semantic shortcuts. Finally, extensive experiments over 7 datasets and 12 downstream tasks demonstrate the superiority of ZeroRel. Furthermore, ZeroRel trained without any task-specific labels achieves an average improvement of 6.24% over models trained with supervised labels.

End-to-End Hyper-Relational Information Extraction for Engineering Diagrams via Dynamically Tokenized Relation Transformer

Provisioning An Adaptive Model to Analyze Uncertainty and Large Language Patterns for Enhanced Document Re-Ranking

This work introduces a trust based adaptive reranking model- ATM (Adaptive Trust Model) that allocates computational resources according to file level uncertainty, instead of assigning a fixed number of reranker calls per query, which focuses computation only where ranking confidence is low.