DEPTH: Hallucination-Free Relation Extraction via Dependency-Aware Sentence Simplification and Two-tiered Hierarchical Refinement

• URL: http://arxiv.org/abs/2508.14391v1
• Date: Wed, 20 Aug 2025 03:35:24 GMT
• Title: DEPTH: Hallucination-Free Relation Extraction via Dependency-Aware Sentence Simplification and Two-tiered Hierarchical Refinement
• Authors: Yupei Yang, Fan Feng, Lin Yang, Wanxi Deng, Lin Qu, Biwei Huang, Shikui Tu, Lei Xu,
• Abstract summary: DEPTH is a framework that integrates Dependency-aware sEntence simPlification and Two-tiered Hierarchical refinement into the relation extraction pipeline.<n>We show that DEPTH reduces the average hallucination rate to 7.0% while achieving a 17.2% improvement in average F1 score over state-of-the-art baselines.
• Score: 22.164114662885652
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Relation extraction enables the construction of structured knowledge for many downstream applications. While large language models (LLMs) have shown great promise in this domain, most existing methods concentrate on relation classification, which predicts the semantic relation type between a related entity pair. However, we observe that LLMs often struggle to reliably determine whether a relation exists, especially in cases involving complex sentence structures or intricate semantics, which leads to spurious predictions. Such hallucinations can introduce noisy edges in knowledge graphs, compromising the integrity of structured knowledge and downstream reliability. To address these challenges, we propose DEPTH, a framework that integrates Dependency-aware sEntence simPlification and Two-tiered Hierarchical refinement into the relation extraction pipeline. Given a sentence and its candidate entity pairs, DEPTH operates in two stages: (1) the Grounding module extracts relations for each pair by leveraging their shortest dependency path, distilling the sentence into a minimal yet coherent relational context that reduces syntactic noise while preserving key semantics; (2) the Refinement module aggregates all local predictions and revises them based on a holistic understanding of the sentence, correcting omissions and inconsistencies. We further introduce a causality-driven reward model that mitigates reward hacking by disentangling spurious correlations, enabling robust fine-tuning via reinforcement learning with human feedback. Experiments on six benchmarks demonstrate that DEPTH reduces the average hallucination rate to 7.0\% while achieving a 17.2\% improvement in average F1 score over state-of-the-art baselines.

Related papers

• CoG: Controllable Graph Reasoning via Relational Blueprints and Failure-Aware Refinement over Knowledge Graphs [53.199517625701475]
  CoG is a training-free framework inspired by Dual-Process Theory that mimics the interplay between intuition and deliberation.<n>CoG significantly outperforms state-of-the-art approaches in both accuracy and efficiency.
  arXiv  Detail & Related papers  (2026-01-16T07:27:40Z)
• Improving LLM Reasoning with Homophily-aware Structural and Semantic Text-Attributed Graph Compression [55.51959317490934]
  Large language models (LLMs) have demonstrated promising capabilities in Text-Attributed Graph (TAG) understanding.<n>We argue that graphs inherently contain rich structural and semantic information, and that their effective exploitation can unlock potential gains in LLMs reasoning performance.<n>We propose Homophily-aware Structural and Semantic Compression for LLMs (HS2C), a framework centered on exploiting graph homophily.
  arXiv  Detail & Related papers  (2026-01-13T03:35:18Z)
• Relation as a Prior: A Novel Paradigm for LLM-based Document-level Relation Extraction [4.476410350566294]
  We propose a novel Relation as a Prior (RelPrior) paradigm for LLM-based Document-level Relation Extraction (DocRE)<n>RelPrior utilizes binary relation as a prior to extract and determine whether two entities are correlated, thereby filtering out irrelevant entity pairs.<n>Extensive experiments on two benchmarks demonstrate that RelPrior achieves state-of-the-art performance, surpassing existing LLM-based methods.
  arXiv  Detail & Related papers  (2025-11-11T11:55:27Z)
• DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models [55.30555646945055]
  Text-to-Image (T2I) models are vulnerable to semantic leakage.<n>We introduce DeLeaker, a lightweight approach that mitigates leakage by directly intervening on the model's attention maps.<n>SLIM is the first dataset dedicated to semantic leakage.
  arXiv  Detail & Related papers  (2025-10-16T17:39:21Z)
• Relation-R1: Progressively Cognitive Chain-of-Thought Guided Reinforcement Learning for Unified Relation Comprehension [31.952192907460713]
  Relation-R1 is the textitfirst unified relation comprehension framework.<n>It integrates cognitive chain-of-thought (CoT)-guided supervised fine-tuning (SFT) and group relative policy optimization ( GRPO)<n>Experiments on widely-used PSG and SWiG datasets demonstrate that Relation-R1 achieves state-of-the-art performance in both binary and textitN-ary relation understanding.
  arXiv  Detail & Related papers  (2025-04-20T14:50:49Z)
• Graph with Sequence: Broad-Range Semantic Modeling for Fake News Detection [18.993270952535465]
  BREAK is a broad-range semantics model for fake news detection.<n>It leverages a fully connected graph to capture comprehensive semantics.<n>It employs dual denoising modules to minimize both structural and feature noise.
  arXiv  Detail & Related papers  (2024-12-07T14:35:46Z)
• Unsupervised Robust Cross-Lingual Entity Alignment via Neighbor Triple Matching with Entity and Relation Texts [17.477542644785483]
  Cross-lingual entity alignment (EA) enables the integration of multiple knowledge graphs (KGs) across different languages.<n>EA pipeline that jointly performs entity-level and Relation-level Alignment by neighbor triple matching strategy.
  arXiv  Detail & Related papers  (2024-07-22T12:25:48Z)
• Prompt-based Logical Semantics Enhancement for Implicit Discourse Relation Recognition [4.7938839332508945]
  We propose a Prompt-based Logical Semantics Enhancement (PLSE) method for Implicit Discourse Relation Recognition (IDRR) Our method seamlessly injects knowledge relevant to discourse relation into pre-trained language models through prompt-based connective prediction. Experimental results on PDTB 2.0 and CoNLL16 datasets demonstrate that our method achieves outstanding and consistent performance against the current state-of-the-art models.
  arXiv  Detail & Related papers  (2023-11-01T08:38:08Z)
• FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network [48.912196729711624]
  Few-shot semantic segmentation is the task of learning to locate each pixel of a novel class in a query image with only a few annotated support images. We propose a Feature-Enhanced Context-Aware Network (FECANet) to suppress the matching noise caused by inter-class local similarity. In addition, we propose a novel correlation reconstruction module that encodes extra correspondence relations between foreground and background and multi-scale context semantic features.
  arXiv  Detail & Related papers  (2023-01-19T16:31:13Z)
• HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extraction [63.64877263289319]
  Unsupervised relation extraction aims to extract the relationship between entities from natural language sentences without prior information on relational scope or distribution.<n>We propose a novel contrastive learning framework named HiURE, which has the capability to derive hierarchical signals from relational feature space using cross hierarchy attention.<n> Experimental results on two public datasets demonstrate the advanced effectiveness and robustness of HiURE on unsupervised relation extraction when compared with state-of-the-art models.
  arXiv  Detail & Related papers  (2022-05-04T17:56:48Z)
• SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction [51.27558374091491]
  We propose to explicitly teach the model to capture relevant contexts and entity types by supervising and augmenting intermediate steps (SAIS) for relation extraction. Based on a broad spectrum of carefully designed tasks, our proposed SAIS method not only extracts relations of better quality due to more effective supervision, but also retrieves the corresponding supporting evidence more accurately.
  arXiv  Detail & Related papers  (2021-09-24T17:37:35Z)
• Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognition [59.52434325897716]
  We propose a solution, named DMUE, to address the problem of annotation ambiguity from two perspectives. For the former, an auxiliary multi-branch learning framework is introduced to better mine and describe the latent distribution in the label space. For the latter, the pairwise relationship of semantic feature between instances are fully exploited to estimate the ambiguity extent in the instance space.
  arXiv  Detail & Related papers  (2021-04-01T03:21:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.