Jun 2026· 2026 11th International Conference on Electronic Technology and Information Science (ICETIS)· pp. 238-241· 0 citations· 9 references
Abstract
Document-level relation extraction (DocRE) identifies semantic relations between entity pairs in a document, but its progress is limited by the scarcity of high-quality annotations. Distant supervision alleviates this issue by automatically constructing large-scale training data, yet it also introduces noisy and incomplete labels. To address these problems, we propose LCDS, a logic-constrained distant supervision framework for DocRE. LCDS first applies Monte Carlo dropout to estimate prediction uncertainty and filter unreliable pseudo labels. It then mines high-confidence logical rules from human-annotated data and uses them to complement missing relations and correct conflicts. Through iterative training, LCDS progressively improves pseudo-label quality. Experiments on DocRED and Re-DocRED show that LCDS achieves F1 scores of 67.39% and $\mathbf{8 1. 4 2 \%}$, respectively, outperforming previous state-of-theart models and demonstrating the effectiveness of combining uncertainty estimation with logical reasoning.
This work introduces an ontology-driven framework to quantify and enforce structural consistency in DocRE datasets and reveals substantial structural noise in DocRED distant and demonstrates that such inconsistencies propagate to model predictions.
Laura Menotti, Stefano Marchesin, Gianmaria Silvello· 0 citations
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.
The ATGL serves as a general optimization objective that can be readily applied to different DocRE models and outperforms other DocRE losses and achieves state-of-the-art results, while consistently improving the performance of existing DocRE models.
Huangming Xu, Fu Zhang, Zhixuan Yang et al.· Annual Meeting of the Associ...· 0 citations
Long-document question-answering experiments show that human-verified TOC hierarchies and contextual relationships improve reasoning, with their combination providing complementary benefits.
Yuefeng Zou, Yichen Lu, Jingxiao Yang et al.· 0 citations