mlsanityData to 7 Oct 2026

RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction

arXiv 2203.09101 ↗First posted 17 Mar 2022cs.CLcited by 60

On the map: Synthetic data and self-improvement for LLMs → LLM synthetic data generation

Abstract (arXiv)

Despite the importance of relation extraction in building and representing knowledge, less research is focused on generalizing to unseen relations types. We introduce the task setting of Zero-Shot Relation Triplet Extraction (ZeroRTE) to encourage further research in low-resource relation extraction methods. Given an input sentence, each extracted triplet consists of the head entity, relation label, and tail entity where the relation label is not seen at the training stage. To solve ZeroRTE, we propose to synthesize relation examples by prompting language models to generate structured texts. Concretely, we unify language model prompts and structured text approaches to design a structured prompt template for generating synthetic relation samples when conditioning on relation label prompts (RelationPrompt). To overcome the limitation for extracting multiple relation triplets in a sentence, we design a novel Triplet Search Decoding method. Experiments on FewRel and Wiki-ZSL datasets show the efficacy of RelationPrompt for the ZeroRTE task and zero-shot relation classification. Our code and data are available at github.com/declare-lab/RelationPrompt.

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). Placed in LLM synthetic data generation, one of 13 directions in Synthetic data and self-improvement for LLMs. Builds on 30 of its 41 references that are in the map. First posted on arXiv 17 Mar 2022.

Builds on

30 of 41 references.

References · 30

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  4. 2019Language Models as Knowledge Bases?cited by 1,922
  5. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  6. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  7. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 800
  8. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  9. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 713
  10. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 599
  11. 2017Zero-Shot Relation Extraction via Reading Comprehensioncited by 425
  12. 2018FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluationcited by 254
18 more
  1. 2022ZeroGen: Efficient Zero-shot Learning via Dataset Generationcited by 209
  2. 2018Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relationscited by 201
  3. 2022Generating Training Data with Language Models: Towards Zero-Shot Language Understandingcited by 199
  4. 2021Structured Prediction as Translation between Augmented Natural Languagescited by 183
  5. 2021Template-Based Named Entity Recognition Using BARTcited by 153
  6. 2019Entity-Relation Extraction as Multi-Turn Question Answeringcited by 96
  7. 2020Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoderscited by 87
  8. 2019Enriching Pre-trained Language Model with Entity Information for Relation Classificationcited by 82
  9. 2019Effective Modeling of Encoder-Decoder Architecture for Joint Entity and Relation Extractioncited by 73
  10. 2015Reasoning about Entailment with Neural Attentioncited by 68
  11. 2017Zero-Shot Transfer Learning for Event Extractioncited by 66
  12. 2021Learning Span-Level Interactions for Aspect Sentiment Triplet Extractioncited by 60
  13. 2019Zero-shot Text Classification With Generative Language Modelscited by 55
  14. 2021Neural Data Augmentation via Example Extrapolationcited by 54
  15. 2021ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learningcited by 46
  16. 2020DARE: Data Augmented Relation Extraction with GPT-2cited by 43
  17. 2016Question Answering on Freebase via Relation Extraction and Textual Evidencecited by 39
  18. 2017Train Once, Test Anywhere: Zero-Shot Learning for Text Classificationcited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 10; 2023: 19; 2024: 16; 2025: 11; 2026: 4.

60 papers.

Sort:

By area:

  1. 2023Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Biascited by 230
  2. 2023InstructUIE: Multi-task Instruction Tuning for Unified Information Extractioncited by 167
  3. 2022Revisiting DocRED -- Addressing the False Negative Problem in Relation Extractioncited by 57
  4. 2022Language Models in the Loop: Incorporating Prompting into Weak Supervisioncited by 51
  5. 2024Forcing Diffuse Distributions out of Language Modelscited by 48
  6. 2022Improving Aspect Sentiment Quad Prediction via Template-Order Data Augmentationcited by 29
  7. 2023Revisiting Large Language Models as Zero-shot Relation Extractorscited by 29
  8. 2023CodeKGC: Code Language Model for Generative Knowledge Graph Constructioncited by 28
  9. 2023On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Trainingcited by 20
  10. 2024Retrieval Helps or Hurts? A Deeper Dive into the Efficacy of Retrieval Augmentation to Language Modelscited by 19
  11. 2023TarGEN: Targeted Data Generation with Large Language Modelscited by 17
  12. 2024Generative Text Steganography with Large Language Modelcited by 16
38 more
  1. 2024UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Constructioncited by 15
  2. 2024Consistency Guided Knowledge Retrieval and Denoising in LLMs for Zero-shot Document-level Relation Triplet Extractioncited by 14
  3. 2022A Dataset for Hyper-Relational Extraction and a Cube-Filling Approachcited by 13
  4. 2023RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation Extractioncited by 13
  5. 2024Meta In-Context Learning Makes Large Language Models Better Zero and Few-Shot Relation Extractorscited by 13
  6. 2025Time Series Language Model for Descriptive Caption Generationcited by 11
  7. 2022SentBS: Sentence-level Beam Search for Controllable Summarizationcited by 10
  8. 2023A Survey of Graph Prompting Methods: Techniques, Applications, and Challengescited by 10
  9. 2024Unleashing the Power of Large Language Models in Zero-shot Relation Extraction via Self-Promptingcited by 10
  10. 2023AGI for Agriculturecited by 9
  11. 2024Grasping the Essentials: Tailoring Large Language Models for Zero-Shot Relation Extractioncited by 9
  12. 2023Alfred: A System for Prompted Weak Supervisioncited by 8
  13. 2025A Survey on Retrieval And Structuring Augmented Generation with Large Language Modelscited by 8
  14. 2022Zero-shot Triplet Extraction by Template Infillingcited by 7
  15. 2023Zero- and Few-Shots Knowledge Graph Triplet Extraction with Large Language Modelscited by 7
  16. 2024Improving Event Definition Following For Zero-Shot Event Detectioncited by 7
  17. 2022Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Modelscited by 6
  18. 2022Schema-aware Reference as Prompt Improves Data-Efficient Knowledge Graph Constructioncited by 6
  19. 2023UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspectivecited by 6
  20. 2023STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Modelscited by 6
  21. 2024Scaling Knowledge Graph Construction through Synthetic Data Generation and Distillationcited by 6
  22. 2023Easy-to-Hard Learning for Information Extractioncited by 5
  23. 2024IEPile: Unearthing Large-Scale Schema-Based Information Extraction Corpuscited by 5
  24. 2023A Unified Framework for Generative Data Augmentation: A Comprehensive Surveycited by 4
  25. 2024SS-GEN: A Social Story Generation Framework with Large Language Modelscited by 4
  26. 2022Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed Representationscited by 3
  27. 2025GLiDRE: Generalist Lightweight model for Document-level Relation Extractioncited by 3
  28. 2022PCRED: Zero-shot Relation Triplet Extraction with Potential Candidate Relation Selection and Entity Boundary Detectioncited by 2
  29. 2023Weakly-Supervised Questions for Zero-Shot Relation Extractioncited by 2
  30. 2023Class-Adaptive Self-Training for Relation Extraction with Incompletely Annotated Training Datacited by 2
  31. 2023CorefPrompt: Prompt-based Event Coreference Resolution by Measuring Event Type and Argument Compatibilitiescited by 2
  32. 2025Auto-Stega: An Agent-Driven System for Lifelong Strategy Evolution in LLM-Based Text Steganographycited by 2
  33. 2023Generative Meta-Learning for Zero-Shot Relation Triplet Extractioncited by 1
  34. 2024Leveraging Large Language Models for Structure Learning in Prompted Weak Supervisioncited by 1
  35. 2024LLM-Assisted Content Conditional Debiasing for Fair Text Embeddingcited by 1
  36. 2024TPN: Transferable Proto-Learning Network towards Few-shot Document-Level Relation Extractioncited by 1
  37. 2025Biomedical Relation Extraction via Adaptive Document-Relation Cross-Mapping and Concept Unique Identifiercited by 1
  38. 2025Generating Diverse Training Samples for Relation Extraction with Large Language Modelscited by 1

50 most cited of 60 All 60 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Revisiting Relation Extraction in the era of Large Language Models
  2. 2023Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation Extraction
  3. 2024Graph-DPEP: Decomposed Plug and Ensemble Play for Few-Shot Document Relation Extraction with Graph-of-Thoughts Reasoning
  4. 2026Document-Level Zero-Shot Relation Extraction with Entity Side Information
  5. 2026Two-Stage Prompt Optimization for Few-Shot Relation Extraction: From Reasoning-Guided Search to Gradient-Guided Refinement
  6. 2025Hallucination-Resistant Relation Extraction via Dependency-Aware Sentence Simplification and Two-tiered Hierarchical Refinement
  7. 2024Recall, Retrieve and Reason: Towards Better In-Context Relation Extraction
  8. 2026ReaORE: Reasoning-Guided Progressive Open Relation Extraction Empowered by Large Reasoning Models