# Towards Better Graph-based Cross-document Relation Extraction via Non-bridge Entity Enhancement and Prediction Debiasing

arXiv: https://arxiv.org/abs/2406.16529 · HTML: https://mlsanity.com/paper/2406.16529/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 24 Jun 2024.

## Builds on (most cited first, 20 of 20)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [ERNIE: Enhanced Language Representation with Informative Entities](https://mlsanity.com/paper/1905.07129/) (2019)
- [LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention](https://mlsanity.com/paper/2010.01057/) (2020)
- [Graph Convolution over Pruned Dependency Trees Improves Relation Extraction](https://mlsanity.com/paper/1809.10185/) (2018)
- [Towards Debiasing NLU Models from Unknown Biases](https://mlsanity.com/paper/2009.12303/) (2020)
- [Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations](https://mlsanity.com/paper/2205.12685/) (2022)
- [Double Graph Based Reasoning for Document-level Relation Extraction](https://mlsanity.com/paper/2009.13752/) (2020)
- [Zero-shot Temporal Relation Extraction with ChatGPT](https://mlsanity.com/paper/2304.05454/) (2023)
- [Document-Level N-ary Relation Extraction with Multiscale Representation Learning](https://mlsanity.com/paper/1904.02347/) (2019)
- [Classifying Relations by Ranking with Convolutional Neural Networks](https://mlsanity.com/paper/1504.06580/) (2015)
- [Discriminative Reasoning for Document-level Relation Extraction](https://mlsanity.com/paper/2106.01562/) (2021)
- [Graph-based Neural Sentence Ordering](https://mlsanity.com/paper/1912.07225/) (2019)
- [Entity-centered Cross-document Relation Extraction](https://mlsanity.com/paper/2210.16541/) (2022)
- [Uncertainty Calibration for Ensemble-Based Debiasing Methods](https://mlsanity.com/paper/2111.04104/) (2021)
- [Robust Natural Language Understanding with Residual Attention Debiasing](https://mlsanity.com/paper/2305.17627/) (2023)
- [Towards Better Document-level Relation Extraction via Iterative Inference](https://mlsanity.com/paper/2211.14470/) (2022)
- [Comparable Demonstrations are Important in In-Context Learning: A Novel Perspective on Demonstration Selection](https://mlsanity.com/paper/2312.07476/) (2023)
- [Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings](https://mlsanity.com/paper/2110.06446/) (2021)

## Built on by (most cited first, 3 of 3)

- [HCRE: LLM-based Hierarchical Classification for Cross-Document Relation Extraction with a Prediction-then-Verification Strategy](https://mlsanity.com/paper/2604.07937/) (2026)
- [LLM-OREF: An Open Relation Extraction Framework Based on Large Language Models](https://mlsanity.com/paper/2509.15089/) (2025)
- [Overlap, Unique and Conflict: Can LLMs Extract What They Can Recognize?](https://mlsanity.com/paper/2609.38799/) (2026)

## Abstract (arXiv)

Cross-document Relation Extraction aims to predict the relation between target entities located in different documents. In this regard, the dominant models commonly retain useful information for relation prediction via bridge entities, which allows the model to elaborately capture the intrinsic interdependence between target entities. However, these studies ignore the non-bridge entities, each of which co-occurs with only one target entity and offers the semantic association between target entities for relation prediction. Besides, the commonly-used dataset--CodRED contains substantial NA instances, leading to the prediction bias during inference. To address these issues, in this paper, we propose a novel graph-based cross-document RE model with non-bridge entity enhancement and prediction debiasing. Specifically, we use a unified entity graph to integrate numerous non-bridge entities with target entities and bridge entities, modeling various associations between them, and then use a graph recurrent network to encode this graph. Finally, we introduce a novel debiasing strategy to calibrate the original prediction distribution. Experimental results on the closed and open settings show that our model significantly outperforms all baselines, including the GPT-3.5-turbo and InstructUIE, achieving state-of-the-art performance. Particularly, our model obtains 66.23% and 55.87% AUC points in the official leaderboardfootnoteurlhttps://codalab.lisn.upsaclay.fr/competitions/3770#results under the two settings, respectively, ranking the first place in all submissions since December 2023. Our code is available at https://github.com/DeepLearnXMU/CoRE-NEPD.