mlsanityData to 7 Oct 2026

Multi-hop Evidence Retrieval for Cross-document Relation Extraction

arXiv 2212.10786 ↗First posted 21 Dec 2022cs.CL cs.IR cs.LGcited by 13

Not on the map. Why?

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.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 31 of its 57 references that are in the map. First posted on arXiv 21 Dec 2022.

Builds on

31 of 57 references.

References · 31

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  4. 2020Longformer: The Long-Document Transformercited by 3,362
  5. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  6. 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 591
  7. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  8. 2019Knowledge Enhanced Contextual Word Representationscited by 294
  9. 2019DocRED: A Large-Scale Document-Level Relation Extraction Datasetcited by 239
  10. 2019KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoningcited by 216
  11. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  12. 2020Answering Complex Open-Domain Questions with Multi-Hop Dense Retrievalcited by 160
19 more
  1. 2022Dense Text Retrieval based on Pretrained Language Models: A Surveycited by 136
  2. 2020Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Poolingcited by 115
  3. 2020Knowledge-Grounded Dialogue Generation with Pre-trained Language Modelscited by 107
  4. 2020Double Graph Based Reasoning for Document-level Relation Extractioncited by 87
  5. 2021An Improved Baseline for Sentence-level Relation Extractioncited by 80
  6. 2021Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrievalcited by 63
  7. 2020More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extractioncited by 52
  8. 2022Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillationcited by 39
  9. 2019Multi-Hop Paragraph Retrieval for Open-Domain Question Answeringcited by 34
  10. 2021Phrase Retrieval Learns Passage Retrieval, Toocited by 33
  11. 2021Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusioncited by 28
  12. 2020Analogous Process Structure Induction for Sub-event Sequence Predictioncited by 26
  13. 2021Discriminative Reasoning for Document-level Relation Extractioncited by 25
  14. 2019Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answeringcited by 20
  15. 2022Entity-centered Cross-document Relation Extractioncited by 18
  16. 2021Three Sentences Are All You Need: Local Path Enhanced Document Relation Extractioncited by 16
  17. 2022Generative Multi-hop Retrievalcited by 10
  18. 2021Discourse-level Relation Extraction via Graph Poolingcited by 9
  19. 2020Towards Accurate and Consistent Evaluation: A Dataset for Distantly-Supervised Relation Extractioncited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 4; 2025: 1; 2026: 4.

13 papers.

Sort:

By area:

  1. 2023Enhanced Chart Understanding in Vision and Language Task via Cross-modal Pre-training on Plot Table Pairscited by 15
  2. 2023Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuningcited by 8
  3. 2023Are Large Language Models Good Fact Checkers: A Preliminary Studycited by 8
  4. 2023STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Modelscited by 6
  5. 2024Familiarity-Aware Evidence Compression for Retrieval-Augmented Generationcited by 4
  6. 2024Knowledge-Driven Cross-Document Relation Extractioncited by 2
  7. 2024Harvesting Events from Multiple Sources: Towards a Cross-Document Event Extraction Paradigmcited by 2
  8. 2026HCRE: LLM-based Hierarchical Classification for Cross-Document Relation Extraction with a Prediction-then-Verification Strategycited by 2
  9. 2024Reward-based Input Construction for Cross-document Relation Extractioncited by 1
  10. 2025Inferring from Logits: Exploring Best Practices for Decoding-Free Generative Candidate Selectioncited by 1
  11. 2026HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific Literaturecited by 0
  12. 2026Evidence Blindness in Direct Corpus Interaction: Persistent Navigation with AtlasNavcited by 0
1 more
  1. 2026ConRAG: Lightweight inference of multi-hop relationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026EvLink: Source-Grounded Evidence Linking for Graph RAG
  2. 2026HyCE-RAG: Hypergraph Chain-of-Evidence Retrieval-Augmented Generation for Explainable Multi-hop Question Answering
  3. 2026Query, Decompose, Compress: Structured Query Expansion for Efficient Multi-Hop Retrieval
  4. 2023Document-level Relation Extraction with Cross-sentence Reasoning Graph
  5. 2026Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval
  6. 2022A Densely Connected Criss-Cross Attention Network for Document-level Relation Extraction
  7. 2026DynaKRAG: A Unified Framework for Learnable Evidence Control in Multi-Hop Retrieval-Augmented Generation
  8. 2026Toward Robust GraphRAG: Mitigating Retrieval Drift and Hallucination from Imperfect Knowledge Graphs