# Grasping the Essentials: Tailoring Large Language Models for Zero-Shot Relation Extraction

arXiv: https://arxiv.org/abs/2402.11142 · HTML: https://mlsanity.com/paper/2402.11142/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 52 references that are in the map.
- First posted on arXiv 17 Feb 2024.

## Builds on (most cited first, 30 of 37)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Zero-Shot Relation Extraction via Reading Comprehension](https://mlsanity.com/paper/1706.04115/) (2017)
- [LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention](https://mlsanity.com/paper/2010.01057/) (2020)
- [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)
- [PTR: Prompt Tuning with Rules for Text Classification](https://mlsanity.com/paper/2105.11259/) (2021)
- [Generating Training Data with Language Models: Towards Zero-Shot Language Understanding](https://mlsanity.com/paper/2202.04538/) (2022)
- [KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction](https://mlsanity.com/paper/2104.07650/) (2021)
- [Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!](https://mlsanity.com/paper/2303.08559/) (2023)
- [Revisiting Relation Extraction in the era of Large Language Models](https://mlsanity.com/paper/2305.05003/) (2023)
- [Re-TACRED: Addressing Shortcomings of the TACRED Dataset](https://mlsanity.com/paper/2104.08398/) (2021)
- [Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction](https://mlsanity.com/paper/2109.03659/) (2021)
- [Evaluating Large Language Models on Controlled Generation Tasks](https://mlsanity.com/paper/2310.14542/) (2023)
- [Thread of Thought Unraveling Chaotic Contexts](https://mlsanity.com/paper/2311.08734/) (2023)
- [RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction](https://mlsanity.com/paper/2203.09101/) (2022)
- [More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction](https://mlsanity.com/paper/2004.03186/) (2020)
- [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)
- [Synthetic Dialogue Dataset Generation using LLM Agents](https://mlsanity.com/paper/2401.17461/) (2024)
- [Neural Snowball for Few-Shot Relation Learning](https://mlsanity.com/paper/1908.11007/) (2019)
- [Open-Domain Hierarchical Event Schema Induction by Incremental Prompting and Verification](https://mlsanity.com/paper/2307.01972/) (2023)

## Built on by (most cited first, 9 of 9)

- [Refiner: Restructure Retrieval Content Efficiently to Advance Question-Answering Capabilities](https://mlsanity.com/paper/2406.11357/) (2024)
- [A Survey on Retrieval And Structuring Augmented Generation with Large Language Models](https://mlsanity.com/paper/2509.10697/) (2025)
- [Learning to Generate and Extract: A Multi-Agent Collaboration Framework For Zero-shot Document-level Event Arguments Extraction](https://mlsanity.com/paper/2603.02909/) (2026)
- [HCRE: LLM-based Hierarchical Classification for Cross-Document Relation Extraction with a Prediction-then-Verification Strategy](https://mlsanity.com/paper/2604.07937/) (2026)
- [Zero-Shot Open-Schema Entity Structure Discovery](https://mlsanity.com/paper/2506.04458/) (2025)
- [Hallucination-Resistant Relation Extraction via Dependency-Aware Sentence Simplification and Two-tiered Hierarchical Refinement](https://mlsanity.com/paper/2508.14391/) (2025)
- [Combining Distantly Supervised Models with In Context Learning for Monolingual and Cross-Lingual Relation Extraction](https://mlsanity.com/paper/2510.18344/) (2025)
- [Relational Probing: LM-to-Graph Adaptation for Financial Prediction](https://mlsanity.com/paper/2604.10212/) (2026)
- [Sub-Billion, Super-Frontier: Small Language Models Rival Zero-Shot Frontier LLMs on General and Literary Relation Extraction](https://mlsanity.com/paper/2606.22606/) (2026)

## Abstract (arXiv)

Relation extraction (RE) aims to identify semantic relationships between entities within text. Despite considerable advancements, existing models predominantly require extensive annotated training data, which is both costly and labor-intensive to collect. Moreover, these models often struggle to adapt to new or unseen relations. Few-shot learning, aiming to lessen annotation demands, typically provides incomplete and biased supervision for target relations, leading to degraded and unstable performance. To accurately and explicitly describe relation semantics while minimizing annotation demands, we explore the definition only zero-shot RE setting where only relation definitions expressed in natural language are used to train a RE model. We introduce REPaL, comprising three stages: (1) We leverage large language models (LLMs) to generate initial seed instances from relation definitions and an unlabeled corpus. (2) We fine-tune a bidirectional Small Language Model (SLM) with initial seeds to learn relations for the target domain. (3) We expand pattern coverage and mitigate bias from initial seeds by integrating feedback from the SLM's predictions on the unlabeled corpus and the synthesis history. To accomplish this, we leverage the multi-turn conversation ability of LLMs to generate new instances in follow-up dialogues, informed by both the feedback and synthesis history. Studies reveal that definition-oriented seed synthesis enhances pattern coverage whereas indiscriminately increasing seed quantity leads to performance saturation. Experiments on two datasets show REPaL significantly improved cost-effective zero-shot performance by large margins.