GLiREL -- Generalist Model for Zero-Shot Relation Extraction

2025-01-06

AI Summary

To address the challenges of identifying unseen relations and low inference efficiency in zero-shot relation extraction, this paper proposes GLiREL, a lightweight and general-purpose model. Methodologically, GLiREL introduces three key innovations: (1) the first zero-shot multi-entity relation classification architecture enabling single forward pass inference; (2) a scalable relation label synthesis protocol that generalizes across diverse relation definitions; and (3) a prompt-driven contrastive learning framework jointly optimizing relation label embedding alignment and a lightweight cross-modal encoder. Evaluated on FewRel and WikiZSL benchmarks, GLiREL achieves state-of-the-art performance in zero-shot relation classification, significantly outperforming existing methods. It delivers substantial improvements in both classification accuracy and inference speed, demonstrating strong generalization to unseen relations while maintaining computational efficiency.

Technology Category

• Reasoning under Uncertainty: Relational Probabilistic Models
• Machine Learning: Statistical Relational/Logic Learning
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

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

Abstract

We introduce GLiREL (Generalist Lightweight model for zero-shot Relation Extraction), an efficient architecture and training paradigm for zero-shot relation classification. Inspired by recent advancements in zero-shot named entity recognition, this work presents an approach to efficiently and accurately predict zero-shot relationship labels between multiple entities in a single forward pass. Experiments using the FewRel and WikiZSL benchmarks demonstrate that our approach achieves state-of-the-art results on the zero-shot relation classification task. In addition, we contribute a protocol for synthetically-generating datasets with diverse relation labels.

Problem

• Relation Extraction
• Zero-shot Learning
• New Relation Identification

Innovation

• Zero-shot Relation Extraction
• Entity Naming Recognition
• Diverse Relational Data Generation