DocKS-RAG: Optimizing Document-Level Relation Extraction through LLM-Enhanced Hybrid Prompt Tuning
Xiaolong Xu, Yibo Zhou, Haolong Xiang, Xiaoyong Li, Xuyun Zhang, Lianyong Qi, Wanchun Dou
Abstract
Document-level relation extraction (RE) aims to extract comprehensive correlations between entities and relations from documents. Most of existing works conduct transfer learning on pretrained language models (PLMs), which allows for richer contextual representation to improve the performance. However, such PLMs-based methods suffer from incorporating structural knowledge, such as entity-entity interactions. Moreover, current works struggle to infer the implicit relations between entities across different sentences, which results in poor prediction. To deal with the above issues, we propose a novel and effective framework, named DocKS-RAG, which introduces extra structural knowledge and semantic information to further enhance the performance of document-level RE. Specifically, we construct a Document-level Knowledge Graph from the observable documentation data to better capture the structural information between entities and relations. Then, a Sentence-level Semantic Retrieval-Augmented Generation mechanism is designed to consider the similarity in different sentences by retrieving the relevant contextual semantic information. Furthermore, we present a hybrid-prompt tuning method on large language models (LLMs) for specific document-level RE tasks. Finally, extensive experiments conducted on two benchmark datasets demonstrate that our proposed framework enhances all the metrics compared with state-ofthe-art methods.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- REBEL: Relation Extraction By End-to-end Language generation cites Effective Modeling of Encoder-Decoder Architecture for Joint Entity and Relation Extraction
- Double Graph Based Reasoning for Document-level Relation Extraction cites Reasoning with Latent Structure Refinement for Document-Level Relation Extraction
Builds on15
- Towards a Unified View of Parameter-Efficient Transfer LearningJunxian He, Chunting Zhou, Xuezhe Ma, Taylor Berg-Kirkpatrick et al.ICLR 2022 · 1,182 citations
- Reasoning with Latent Structure Refinement for Document-Level Relation ExtractionGuoshun Nan, Zhijiang Guo, Ivan Sekulic, Wei LuACL 2020 · 294 citations
- Effective Modeling of Encoder-Decoder Architecture for Joint Entity and Relation ExtractionTapas Nayak, Hwee Tou NgAAAI 2020 · 272 citations
- REBEL: Relation Extraction By End-to-end Language generationPere-Lluís Huguet Cabot, Roberto NavigliEMNLP Findings 2021 · 262 citations
- Double Graph Based Reasoning for Document-level Relation ExtractionShuang Zeng, Runxin Xu, Baobao Chang, Lei LiEMNLP 2020 · 238 citations
Related papers
- Revisiting Document-Level Relation Extraction with Context-Guided Link PredictionMonika Jain, Raghava Mutharaju, Ramakanth Kavuluru, Kuldeep SinghAAAI 2024 · 17 citations
- TAdaRAG: Task Adaptive Retrieval-Augmented Generation via On-the-Fly Knowledge Graph ConstructionJie Zhang, Bo Tang, Wanzi Shao, Wenqiang Wei et al.AAAI 2026
- On the Role of Discriminative Models in Generative Relation ExtractionGuozheng Li, Peng Wang, Zijie Xu, Jing Zhou et al.ACL 2026
- CoRAG: Enhancing Hybrid Retrieval-Augmented Generation through a Cooperative Retriever ArchitectureZaiyi Zheng, Song Wang, Zihan Chen, Yaochen Zhu et al.EMNLP Findings 2025 · 1 citation
- Query-Aware Knowledge Retrieval via Hyperbolic StructuringChuang Zhou, Junnan Dong, Yilin Xiao, Shengyuan Chen et al.ACL 2026
