analiza aiqbench
LELA introduces a zero-shot entity linking framework using large language models, eliminating the need for domain-specific fine-tuning while maintaining high accuracy across diverse knowledge bases and settings. This approach significantly advances information extraction workflows by leveraging LLM capabilities directly without additional training overhead.
LELA: an LLM-based Entity Linking Approach with Zero-Shot Domain Adaptation
arXiv:2601.05192v2 Announce Type: replace Abstract: Entity linking (mapping ambiguous mentions in text to entities in a knowledge base) is a foundational step in tasks such as knowledge graph construction, question-answering, and information extraction. Our method, LELA, is a modular coarse-to-fine approach that leverages the capabilities of large language models (LLMs), and works with different target domains, knowledge bases and LLMs, without any fine-tuning phase. Our experiments across various entity linking settings show that LELA is highly competitive with fine-tuned approaches, and substantially outperforms the non-fine-tuned ones.
Abstract:Entity linking (mapping ambiguous mentions in text to entities in a knowledge base) is a foundational step in tasks such as knowledge graph construction, question-answering, and information extraction. Our method, LELA, is a modular coarse-to-fine approach that leverages the capabilities of large language models (LLMs), and works with different target domains, knowledge bases and LLMs, without any fine-tuning phase. Our experiments across various entity linking settings show that LELA is highly competitive with fine-tuned approaches, and substantially outperforms the non-fine-tuned ones.
Accepted at ISWC 2026. Extended version with appendices
Computation and Language (cs.CL)
arXiv:2601.05192 [cs.CL]
(or arXiv:2601.05192v2 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2601.05192 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 182 cuvinte
Subiecte conexe
Leveraging LLMs for Context-Aware Implicit Textual and Multimodal Hate Speech Detection
arXiv · 11 sept. 2026
News
Quantum Computing Report · 25 iul. 2026
The J-Space Debate, Agent Swarms, and Pacing Frontier AI - Digital Minds Newsletter #4
LessWrong · 18 sept. 2026
Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Batch Processing Framework
arXiv · 16 oct. 2026