GLiNER-Relex: A Unified Framework for Joint Named Entity Recognition and Relation Extraction
Summary
GLiNER-Relex is a unified framework for joint named entity recognition and relation extraction that leverages a shared transformer encoder for zero-shot capabilities. The paper demonstrates competitive performance on standard benchmarks and releases the model as an open-source Python package.
View Cached Full Text
Cached at: 05/13/26, 08:11 AM
Paper page - GLiNER-Relex: A Unified Framework for Joint Named Entity Recognition and Relation Extraction
Source: https://huggingface.co/papers/2605.10108
Abstract
A unified model for joint named entity recognition and relation extraction that uses a shared transformer encoder to simultaneously identify entities and extract relations with zero-shot capabilities.
Joint named entity recognition(NER) andrelation extraction(RE) is a fundamental task in natural language processing for constructing knowledge graphs from unstructured text. While recent approaches treat NER and RE as separate tasks requiring distinct models, we introduceGLiNER-Relex, a unified architecture that extends theGLiNERframework to perform both entity recognition andrelation extractionin a single model. Our approach leverages a sharedbidirectional transformer encoderto jointly represent text, entity type labels, and relation type labels, enablingzero-shot extractionof arbitrary entity and relation types specified at inference time.GLiNER-Relex constructsentity pair representationsfrom recognized spans and scores them against relation type embeddings using a dedicatedrelation scoring module. We evaluate our model on four standardrelation extractionbenchmarks:CoNLL04,DocRED,FewRel, andCrossRE, and demonstrate competitive performance against both specializedrelation extractionmodels and large language models, while maintaining the computational efficiency characteristic of theGLiNERfamily. The model is released as an open-source Python package with a simple inference API that allows users to specify arbitrary entity and relation type labels at inference time and obtain both entities and relation triplets in a single call. All models and code are publicly available.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2605\.10108
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2605.10108 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2605.10108 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2605.10108 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
DE-NER : Zero-shot Named Entity Recognition via Dialogue Elicitation of Large Language Models
Introduces DE-NER, a dialogue elicitation framework for zero-shot named entity recognition that uses self-play between questioner and roleplayer LLMs to clarify entity boundaries, achieving an average 3.75% F1 improvement over baselines.
Cross-lingual Relation Extraction with Large Language Models: Zero-Shot, Few-Shot, and Fine-Tuned Evaluation on Romanian
This paper investigates cross-lingual relation extraction for Romanian by translating the SemEval-2010 Task 8 benchmark and evaluating Gemma 4 under zero-shot, few-shot, and QLoRA fine-tuning, comparing with smaller encoder baselines.
ANCHOR-RE: An Agentic Neuro-Symbolic Framework for Grounded Biomedical Relation Extraction
ANCHOR-RE is a neuro-symbolic framework that integrates ontology-guided reasoning and external knowledge grounding into LLM inference for biomedical relation extraction, improving F1 scores across multiple benchmarks without fine-tuning.
ReaORE: Reasoning-Guided Progressive Open Relation Extraction Empowered by Large Reasoning Models
Proposes ReaORE, a reasoning-guided framework for open relation extraction that progressively filters and predicts relations via coarse-to-fine reasoning, outperforming existing baselines on two datasets.
IRIS: Reusable Identity Representations from Frozen LLMs for Entity Alignment
IRIS is a training-free framework that uses frozen large language models to construct reusable identity representations for entities in knowledge graphs, enabling efficient entity alignment across different KGs without pair-dependent processing.