# Multi-hop Evidence Retrieval for Cross-document Relation Extraction

arXiv: https://arxiv.org/abs/2212.10786 · HTML: https://mlsanity.com/paper/2212.10786/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 57 references that are in the map.
- First posted on arXiv 21 Dec 2022.

## Builds on (most cited first, 30 of 31)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://mlsanity.com/paper/2004.09813/) (2020)
- [QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://mlsanity.com/paper/2104.06378/) (2021)
- [Knowledge Enhanced Contextual Word Representations](https://mlsanity.com/paper/1909.04164/) (2019)
- [DocRED: A Large-Scale Document-Level Relation Extraction Dataset](https://mlsanity.com/paper/1906.06127/) (2019)
- [KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning](https://mlsanity.com/paper/1909.02151/) (2019)
- [Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering](https://mlsanity.com/paper/2101.00774/) (2021)
- [Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval](https://mlsanity.com/paper/2009.12756/) (2020)
- [Dense Text Retrieval based on Pretrained Language Models: A Survey](https://mlsanity.com/paper/2211.14876/) (2022)
- [Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling](https://mlsanity.com/paper/2010.11304/) (2020)
- [Knowledge-Grounded Dialogue Generation with Pre-trained Language Models](https://mlsanity.com/paper/2010.08824/) (2020)
- [Double Graph Based Reasoning for Document-level Relation Extraction](https://mlsanity.com/paper/2009.13752/) (2020)
- [An Improved Baseline for Sentence-level Relation Extraction](https://mlsanity.com/paper/2102.01373/) (2021)
- [Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval](https://mlsanity.com/paper/2101.00436/) (2021)
- [More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction](https://mlsanity.com/paper/2004.03186/) (2020)
- [Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation](https://mlsanity.com/paper/2203.10900/) (2022)
- [Multi-Hop Paragraph Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/1906.06606/) (2019)
- [Phrase Retrieval Learns Passage Retrieval, Too](https://mlsanity.com/paper/2109.08133/) (2021)
- [Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusion](https://mlsanity.com/paper/2106.08657/) (2021)
- [Analogous Process Structure Induction for Sub-event Sequence Prediction](https://mlsanity.com/paper/2010.08525/) (2020)
- [Discriminative Reasoning for Document-level Relation Extraction](https://mlsanity.com/paper/2106.01562/) (2021)
- [Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering](https://mlsanity.com/paper/1909.07598/) (2019)
- [Entity-centered Cross-document Relation Extraction](https://mlsanity.com/paper/2210.16541/) (2022)
- [Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction](https://mlsanity.com/paper/2106.01793/) (2021)
- [Generative Multi-hop Retrieval](https://mlsanity.com/paper/2204.13596/) (2022)
- [Discourse-level Relation Extraction via Graph Pooling](https://mlsanity.com/paper/2101.00124/) (2021)

## Built on by (most cited first, 13 of 13)

- [Enhanced Chart Understanding in Vision and Language Task via Cross-modal Pre-training on Plot Table Pairs](https://mlsanity.com/paper/2305.18641/) (2023)
- [Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuning](https://mlsanity.com/paper/2301.10915/) (2023)
- [Are Large Language Models Good Fact Checkers: A Preliminary Study](https://mlsanity.com/paper/2311.17355/) (2023)
- [STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models](https://mlsanity.com/paper/2305.15090/) (2023)
- [Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation](https://mlsanity.com/paper/2409.12468/) (2024)
- [Knowledge-Driven Cross-Document Relation Extraction](https://mlsanity.com/paper/2405.13546/) (2024)
- [Harvesting Events from Multiple Sources: Towards a Cross-Document Event Extraction Paradigm](https://mlsanity.com/paper/2406.16021/) (2024)
- [HCRE: LLM-based Hierarchical Classification for Cross-Document Relation Extraction with a Prediction-then-Verification Strategy](https://mlsanity.com/paper/2604.07937/) (2026)
- [Reward-based Input Construction for Cross-document Relation Extraction](https://mlsanity.com/paper/2405.20649/) (2024)
- [Inferring from Logits: Exploring Best Practices for Decoding-Free Generative Candidate Selection](https://mlsanity.com/paper/2501.17338/) (2025)
- [HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific Literature](https://mlsanity.com/paper/2603.23136/) (2026)
- [Evidence Blindness in Direct Corpus Interaction: Persistent Navigation with AtlasNav](https://mlsanity.com/paper/2608.24764/) (2026)
- [ConRAG: Lightweight inference of multi-hop relations](https://mlsanity.com/paper/2609.35193/) (2026)

## Abstract (arXiv)

Relation Extraction (RE) has been extended to cross-document scenarios because many relations are not simply described in a single document. This inevitably brings the challenge of efficient open-space evidence retrieval to support the inference of cross-document relations, along with the challenge of multi-hop reasoning on top of entities and evidence scattered in an open set of documents. To combat these challenges, we propose MR.COD (Multi-hop evidence retrieval for Cross-document relation extraction), which is a multi-hop evidence retrieval method based on evidence path mining and ranking. We explore multiple variants of retrievers to show evidence retrieval is essential in cross-document RE. We also propose a contextual dense retriever for this setting. Experiments on CodRED show that evidence retrieval with MR.COD effectively acquires crossdocument evidence and boosts end-to-end RE performance in both closed and open settings.