---
title: "KnowRA: Knowledge Retrieval Augmented Method for Document-level Relation Extraction with Comprehensive Reasoning Abilities"
authors:
  - "Chengcheng Mai"
  - "Yuxiang Wang"
  - "Ziyu Gong"
  - "Hanxiang Wang"
  - "Yihua Huang"
doi: "10.24963/ijcai.2025/910"
url: "https://ijcai.org/proceedings/2025/910"
pdf: "https://ijcai.org/proceedings/2025/0910.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "8186-8194"
track: "Main Track"
keywords:
  - "Data Mining: DM: Mining text, web, social media"
  - "Natural Language Processing: NLP: Information extraction"
  - "Knowledge Representation and Reasoning: KRR: Common-sense reasoning"
  - "Natural Language Processing: NLP: Applications"
---

# KnowRA: Knowledge Retrieval Augmented Method for Document-level Relation Extraction with Comprehensive Reasoning Abilities

Chengcheng Mai, Yuxiang Wang, Ziyu Gong, Hanxiang Wang, Yihua Huang

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 8186-8194. DOI: [10.24963/ijcai.2025/910](https://doi.org/10.24963/ijcai.2025/910)

## Abstract

Document-level relation extraction (Doc-RE) aims to extract relations between entities across multiple sentences. Therefore, Doc-RE requires more comprehensive reasoning abilities like humans, involving complex cross-sentence interactions between entities, contexts, and external general knowledge, compared to the sentence-level RE. However, most existing Doc-RE methods focus on optimizing single reasoning ability, but lack the ability to utilize external knowledge for comprehensive reasoning on long documents. To solve these problems, a knowledge retrieval augmented method, named KnowRA, was proposed with comprehensive reasoning to autonomously determine whether to accept external knowledge to assist Doc-RE. Firstly, we constructed a document graph for semantic encoding and integrated the co-reference resolution model to augment the co-reference reasoning ability. Then, we expanded the document graph into a document knowledge graph by retrieving the external knowledge base for common-sense reasoning and a novel knowledge filtration method was presented to filter out irrelevant knowledge. Finally, we proposed the axis attention mechanism to build direct and indirect associations with intermediary entities for achieving cross-sentence logical reasoning. Extensive experiments conducted on two datasets verified the effectiveness of our method compared to the state-of-the-art baselines. Our code is available at https://anonymous.4open.science/r/KnowRA.