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
DiZiNER: Disagreement-guided Instruction Refinement via Pilot Annotation Simulation for Zero-shot Named Entity Recognition
DiZiNER is a framework that uses disagreement between multiple LLMs to refine task instructions for zero-shot named entity recognition, achieving state-of-the-art results on 14 out of 18 benchmarks and significantly reducing the performance gap between zero-shot and supervised systems.
Retrieve, Integrate, and Synthesize: Spatial-Semantic Grounded Latent Visual Reasoning
This paper introduces RIS, a framework for spatial-semantic grounded latent visual reasoning in Multimodal Large Language Models to overcome information bottlenecks. It proposes anchoring latent tokens to spatial and semantic evidence, showing improvements on benchmarks like V* and HRBench.
@mayhewsw: New paper: I know the hotness is all in 10xing compute scale, and telling things to think step by step with tool use, b…
Authors release Universal NER v2, a named-entity recognition paper presented at LREC 2026 that deliberately eschews modern scaling and tool-use trends.
GATHER: Convergence-Centric Hyper-Entity Retrieval for Zero-Shot Cell-Type Annotation
This paper introduces GATHER, a convergence-centric retrieval method for zero-shot cell-type annotation using knowledge graphs, which improves accuracy and reduces LLM costs compared to existing KG-RAG baselines.
GiLT: Augmenting Transformer Language Models with Dependency Graphs
The paper proposes GiLT (Graph-Infused Layers Transformer Language Model), which improves syntactic generalization by modulating attention weights using features from dependency graphs constructed incrementally during token prediction, outperforming baselines while maintaining competitive perplexity.