# COMM:Concentrated Margin Maximization for Robust Document-Level Relation Extraction

arXiv: https://arxiv.org/abs/2503.13885 · HTML: https://mlsanity.com/paper/2503.13885/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 27 references that are in the map.
- First posted on arXiv 18 Mar 2025.

## Builds on (most cited first, 14 of 14)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling](https://mlsanity.com/paper/2010.11304/) (2020)
- [Double Graph Based Reasoning for Document-level Relation Extraction](https://mlsanity.com/paper/2009.13752/) (2020)
- [Coreferential Reasoning Learning for Language Representation](https://mlsanity.com/paper/2004.06870/) (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)
- [FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering](https://mlsanity.com/paper/2308.12060/) (2023)
- [Relation Classification with Entity Type Restriction](https://mlsanity.com/paper/2105.08393/) (2021)
- [SIRE: Separate Intra- and Inter-sentential Reasoning for Document-level Relation Extraction](https://mlsanity.com/paper/2106.01709/) (2021)
- [Document-level Relation Extraction with Cross-sentence Reasoning Graph](https://mlsanity.com/paper/2303.03912/) (2023)
- [Bridging the Language Gap: Knowledge Injected Multilingual Question Answering](https://mlsanity.com/paper/2304.03159/) (2023)

## Built on by (most cited first, 1 of 1)

- [DOREMI: Optimizing Long Tail Predictions in Document-Level Relation Extraction](https://mlsanity.com/paper/2601.11190/) (2026)

## Abstract (arXiv)

Document-level relation extraction (DocRE) is the process of identifying and extracting relations between entities that span multiple sentences within a document. Due to its realistic settings, DocRE has garnered increasing research attention in recent years. Previous research has mostly focused on developing sophisticated encoding models to better capture the intricate patterns between entity pairs. While these advancements are undoubtedly crucial, an even more foundational challenge lies in the data itself. The complexity inherent in DocRE makes the labeling process prone to errors, compounded by the extreme sparsity of positive relation samples, which is driven by both the limited availability of positive instances and the broad diversity of positive relation types. These factors can lead to biased optimization processes, further complicating the task of accurate relation extraction. Recognizing these challenges, we have developed a robust framework called textitCOMM to better solve DocRE. textitCOMM operates by initially employing an instance-aware reasoning method to dynamically capture pertinent information of entity pairs within the document and extract relational features. Following this, textitCOMM takes into account the distribution of relations and the difficulty of samples to dynamically adjust the margins between prediction logits and the decision threshold, a process we call Concentrated Margin Maximization. In this way, textitCOMM not only enhances the extraction of relevant relational features but also boosts DocRE performance by addressing the specific challenges posed by the data. Extensive experiments and analysis demonstrate the versatility and effectiveness of textitCOMM, especially its robustness when trained on low-quality data (achieves textgreater 10% performance gains).