Structured Semantic Information Helps Retrieve Better Examples for In-Context Learning in Few-Shot Relation Extraction

2026-01-28

AI Summary

This work addresses the challenge of insufficient example quality in few-shot relation extraction by proposing a hybrid strategy that integrates syntactic-semantic structural similarity with examples generated by large language models. For the first time, syntactic-semantic structures are leveraged as the core criterion for retrieving in-context examples, complementing synthetic examples produced by models such as Qwen and Gemma to more comprehensively capture target relations. The proposed approach achieves state-of-the-art performance on FS-TACRED and demonstrates significant improvements on a customized FewRel subset, exhibiting strong cross-dataset and cross-model transferability.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Reasoning under Uncertainty: Relational Probabilistic Models
• Machine Learning: Statistical Relational/Logic Learning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

This paper presents several strategies to automatically obtain additional examples for in-context learning of one-shot relation extraction. Specifically, we introduce a novel strategy for example selection, in which new examples are selected based on the similarity of their underlying syntactic-semantic structure to the provided one-shot example. We show that this method results in complementary word choices and sentence structures when compared to LLM-generated examples. When these strategies are combined, the resulting hybrid system achieves a more holistic picture of the relations of interest than either method alone. Our framework transfers well across datasets (FS-TACRED and FS-FewRel) and LLM families (Qwen and Gemma). Overall, our hybrid selection method consistently outperforms alternative strategies and achieves state-of-the-art performance on FS-TACRED and strong gains on a customized FewRel subset.

Problem

• in-context learning
• few-shot relation extraction
• example retrieval
• structured semantic information
• relation extraction

Innovation

• structured semantic information
• in-context learning
• few-shot relation extraction
• example selection
• hybrid retrieval