# DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extraction

arXiv: https://arxiv.org/abs/2302.08675 · HTML: https://mlsanity.com/paper/2302.08675/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 43 references that are in the map.
- First posted on arXiv 17 Feb 2023.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DocRED: A Large-Scale Document-Level Relation Extraction Dataset](https://mlsanity.com/paper/1906.06127/) (2019)
- [Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling](https://mlsanity.com/paper/2010.11304/) (2020)
- [Cross-Sentence N-ary Relation Extraction with Graph LSTMs](https://mlsanity.com/paper/1708.03743/) (2017)
- [Double Graph Based Reasoning for Document-level Relation Extraction](https://mlsanity.com/paper/2009.13752/) (2020)
- [Document-level Relation Extraction as Semantic Segmentation](https://mlsanity.com/paper/2106.03618/) (2021)
- [Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extraction](https://mlsanity.com/paper/2102.10249/) (2021)
- [Distant Supervision for Relation Extraction beyond the Sentence Boundary](https://mlsanity.com/paper/1609.04873/) (2016)
- [Revisiting DocRED -- Addressing the False Negative Problem in Relation Extraction](https://mlsanity.com/paper/2205.12696/) (2022)
- [Learning Deep Bilinear Transformation for Fine-grained Image Representation](https://mlsanity.com/paper/1911.03621/) (2019)
- [Document-Level N-ary Relation Extraction with Multiscale Representation Learning](https://mlsanity.com/paper/1904.02347/) (2019)
- [Simultaneously Self-Attending to All Mentions for Full-Abstract Biological Relation Extraction](https://mlsanity.com/paper/1802.10569/) (2018)
- [Document-Level Relation Extraction with Reconstruction](https://mlsanity.com/paper/2012.11384/) (2020)
- [Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation](https://mlsanity.com/paper/2203.10900/) (2022)
- [Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains](https://mlsanity.com/paper/2106.13474/) (2021)
- [SIRE: Separate Intra- and Inter-sentential Reasoning for Document-level Relation Extraction](https://mlsanity.com/paper/2106.01709/) (2021)
- [NCRF++: An Open-source Neural Sequence Labeling Toolkit](https://mlsanity.com/paper/1806.05626/) (2018)
- [Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusion](https://mlsanity.com/paper/2106.08657/) (2021)
- [SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction](https://mlsanity.com/paper/2109.12093/) (2021)
- [Denoising Relation Extraction from Document-level Distant Supervision](https://mlsanity.com/paper/2011.03888/) (2020)
- [Does Recommend-Revise Produce Reliable Annotations? An Analysis on Missing Instances in DocRED](https://mlsanity.com/paper/2204.07980/) (2022)
- [Hierarchical Entity Typing via Multi-level Learning to Rank](https://mlsanity.com/paper/2004.02286/) (2020)
- [Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction](https://mlsanity.com/paper/2106.01793/) (2021)
- [Document-Level Relation Extraction with Sentences Importance Estimation and Focusing](https://mlsanity.com/paper/2204.12679/) (2022)

## Built on by (most cited first, 30 of 37)

- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Tasks](https://mlsanity.com/paper/2311.08993/) (2023)
- [RAPL: A Relation-Aware Prototype Learning Approach for Few-Shot Document-Level Relation Extraction](https://mlsanity.com/paper/2310.15743/) (2023)
- [Semi-automatic Data Enhancement for Document-Level Relation Extraction with Distant Supervision from Large Language Models](https://mlsanity.com/paper/2311.07314/) (2023)
- [LLM with Relation Classifier for Document-Level Relation Extraction](https://mlsanity.com/paper/2408.13889/) (2024)
- [GKG-LLM: A Unified Framework for Generalized Knowledge Graph Construction](https://mlsanity.com/paper/2503.11227/) (2025)
- [FCDS: Fusing Constituency and Dependency Syntax into Document-Level Relation Extraction](https://mlsanity.com/paper/2403.01886/) (2024)
- [A Comprehensive Survey of Document-level Relation Extraction (2016-2023)](https://mlsanity.com/paper/2309.16396/) (2023)
- [PromptRE: Weakly-Supervised Document-Level Relation Extraction via Prompting-Based Data Programming](https://mlsanity.com/paper/2310.09265/) (2023)
- [Tree-Planted Transformers: Unidirectional Transformer Language Models with Implicit Syntactic Supervision](https://mlsanity.com/paper/2402.12691/) (2024)
- [FRACAS: A FRench Annotated Corpus of Attribution relations in newS](https://mlsanity.com/paper/2309.10604/) (2023)
- [Anaphor Assisted Document-Level Relation Extraction](https://mlsanity.com/paper/2310.18604/) (2023)
- [TTM-RE: Memory-Augmented Document-Level Relation Extraction](https://mlsanity.com/paper/2406.05906/) (2024)
- [Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels](https://mlsanity.com/paper/2406.16293/) (2024)
- [GADePo: Graph-Assisted Declarative Pooling Transformers for Document-Level Relation Extraction](https://mlsanity.com/paper/2308.14423/) (2023)
- [A LayoutLMv3-Based Model for Enhanced Relation Extraction in Visually-Rich Documents](https://mlsanity.com/paper/2404.10848/) (2024)
- [Reward-based Input Construction for Cross-document Relation Extraction](https://mlsanity.com/paper/2405.20649/) (2024)
- [On the Robustness of Document-Level Relation Extraction Models to Entity Name Variations](https://mlsanity.com/paper/2406.07444/) (2024)
- [GEGA: Graph Convolutional Networks and Evidence Retrieval Guided Attention for Enhanced Document-level Relation Extraction](https://mlsanity.com/paper/2407.21384/) (2024)
- [TWIX: a Two-Stage Approach for End-To-End Named Entity Recognition and Relation Extraction](https://mlsanity.com/paper/2609.00832/) (2026)
- [A Two Dimensional Feature Engineering Method for Relation Extraction](https://mlsanity.com/paper/2404.04959/) (2024)
- [Building a Japanese Document-Level Relation Extraction Dataset Assisted by Cross-Lingual Transfer](https://mlsanity.com/paper/2404.16506/) (2024)
- [End-to-End Trainable Retrieval-Augmented Generation for Relation Extraction](https://mlsanity.com/paper/2406.03790/) (2024)
- [Augmenting Document-level Relation Extraction with Efficient Multi-Supervision](https://mlsanity.com/paper/2407.01026/) (2024)
- [Graph-DPEP: Decomposed Plug and Ensemble Play for Few-Shot Document Relation Extraction with Graph-of-Thoughts Reasoning](https://mlsanity.com/paper/2411.02864/) (2024)
- [CDER: Collaborative Evidence Retrieval for Document-level Relation Extraction](https://mlsanity.com/paper/2504.06529/) (2025)
- [Analyzing the Influence of Knowledge Graph Information on Relation Extraction](https://mlsanity.com/paper/2506.16343/) (2025)
- [DISCIE -- Discriminative Closed Information Extraction](https://mlsanity.com/paper/2506.16348/) (2025)
- [Multi-Relation Extraction in Entity Pairs using Global Context](https://mlsanity.com/paper/2507.22926/) (2025)
- [An Senegalese Legal Texts Structuration Using LLM-augmented Knowledge Graph](https://mlsanity.com/paper/2510.02353/) (2025)

## Abstract (arXiv)

Document-level relation extraction (DocRE) is the task of identifying all relations between each entity pair in a document. Evidence, defined as sentences containing clues for the relationship between an entity pair, has been shown to help DocRE systems focus on relevant texts, thus improving relation extraction. However, evidence retrieval (ER) in DocRE faces two major issues: high memory consumption and limited availability of annotations. This work aims at addressing these issues to improve the usage of ER in DocRE. First, we propose DREEAM, a memory-efficient approach that adopts evidence information as the supervisory signal, thereby guiding the attention modules of the DocRE system to assign high weights to evidence. Second, we propose a self-training strategy for DREEAM to learn ER from automatically-generated evidence on massive data without evidence annotations. Experimental results reveal that our approach exhibits state-of-the-art performance on the DocRED benchmark for both DocRE and ER. To the best of our knowledge, DREEAM is the first approach to employ ER self-training.