# Unleashing the Power of Large Language Models in Zero-shot Relation Extraction via Self-Prompting

arXiv: https://arxiv.org/abs/2410.01154 · HTML: https://mlsanity.com/paper/2410.01154/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 2 Oct 2024.

## Builds on (most cited first, 27 of 27)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Zero-Shot Relation Extraction via Reading Comprehension](https://mlsanity.com/paper/1706.04115/) (2017)
- [Generate rather than Retrieve: Large Language Models are Strong Context Generators](https://mlsanity.com/paper/2209.10063/) (2022)
- [FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation](https://mlsanity.com/paper/1810.10147/) (2018)
- [ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT](https://mlsanity.com/paper/2302.10205/) (2023)
- [Generated Knowledge Prompting for Commonsense Reasoning](https://mlsanity.com/paper/2110.08387/) (2021)
- [ZeroGen: Efficient Zero-shot Learning via Dataset Generation](https://mlsanity.com/paper/2202.07922/) (2022)
- [Enhanced LSTM for Natural Language Inference](https://mlsanity.com/paper/1609.06038/) (2016)
- [Diverse Demonstrations Improve In-context Compositional Generalization](https://mlsanity.com/paper/2212.06800/) (2022)
- [Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions](https://mlsanity.com/paper/2306.04140/) (2023)
- [Finding Support Examples for In-Context Learning](https://mlsanity.com/paper/2302.13539/) (2023)
- [Enriching Pre-trained Language Model with Entity Information for Relation Classification](https://mlsanity.com/paper/1905.08284/) (2019)
- [Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction](https://mlsanity.com/paper/2109.03659/) (2021)
- [Reasoning about Entailment with Neural Attention](https://mlsanity.com/paper/1509.06664/) (2015)
- [RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction](https://mlsanity.com/paper/2203.09101/) (2022)
- [Better Zero-Shot Reasoning with Self-Adaptive Prompting](https://mlsanity.com/paper/2305.14106/) (2023)
- [ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learning](https://mlsanity.com/paper/2104.04697/) (2021)
- [Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors](https://mlsanity.com/paper/2305.11159/) (2023)
- [Summarization as Indirect Supervision for Relation Extraction](https://mlsanity.com/paper/2205.09837/) (2022)
- [Contrastive Learning of Sentence Embeddings from Scratch](https://mlsanity.com/paper/2305.15077/) (2023)
- [What do You Mean by Relation Extraction? A Survey on Datasets and Study on Scientific Relation Classification](https://mlsanity.com/paper/2204.13516/) (2022)
- [RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation Extraction](https://mlsanity.com/paper/2306.04954/) (2023)
- [Elaboration-Generating Commonsense Question Answering at Scale](https://mlsanity.com/paper/2209.01232/) (2022)

## Built on by (most cited first, 10 of 10)

- [Can Large Language Models be Effective Online Opinion Miners?](https://mlsanity.com/paper/2505.15695/) (2025)
- [From Fragment to One Piece: A Survey on AI-Driven Graphic Design](https://mlsanity.com/paper/2503.18641/) (2025)
- [Extracting Events Like Code: A Multi-Agent Programming Framework for Zero-Shot Event Extraction](https://mlsanity.com/paper/2511.13118/) (2025)
- [Relation Extraction or Pattern Matching? Unravelling the Generalisation Limits of Language Models for Biographical RE](https://mlsanity.com/paper/2505.12533/) (2025)
- [StructSynth: Dependency Graphs as Generation Plans for Low-Data Tabular Synthesis with Language Models](https://mlsanity.com/paper/2508.02601/) (2025)
- [Hallucination-Resistant Relation Extraction via Dependency-Aware Sentence Simplification and Two-tiered Hierarchical Refinement](https://mlsanity.com/paper/2508.14391/) (2025)
- [Adapting Small Language Models to Low-Resource Domains: A Case Study in Hindi Tourism QA](https://mlsanity.com/paper/2510.25273/) (2025)
- [Relation Extraction Capabilities of LLMs on Clinical Text: A Bilingual Evaluation for English and Turkish](https://mlsanity.com/paper/2601.09367/) (2026)
- [ANCHOR-RE: An Agentic Neuro-Symbolic Framework for Grounded Biomedical Relation Extraction](https://mlsanity.com/paper/2608.03154/) (2026)
- [RePair: Turning Retrieval Failures into Counterfactual Hard Pairs](https://mlsanity.com/paper/2608.29604/) (2026)

## Abstract (arXiv)

Recent research in zero-shot Relation Extraction (RE) has focused on using Large Language Models (LLMs) due to their impressive zero-shot capabilities. However, current methods often perform suboptimally, mainly due to a lack of detailed, context-specific prompts needed for understanding various sentences and relations. To address this, we introduce the Self-Prompting framework, a novel method designed to fully harness the embedded RE knowledge within LLMs. Specifically, our framework employs a three-stage diversity approach to prompt LLMs, generating multiple synthetic samples that encapsulate specific relations from scratch. These generated samples act as in-context learning samples, offering explicit and context-specific guidance to efficiently prompt LLMs for RE. Experimental evaluations on benchmark datasets show our approach outperforms existing LLM-based zero-shot RE methods. Additionally, our experiments confirm the effectiveness of our generation pipeline in producing high-quality synthetic data that enhances performance.