Pré-Publication, Document De Travail Année : 2026

LELA: an LLM-based Entity Linking Approach with Zero-Shot Domain Adaptation

Résumé

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.

Fichier principal
Vignette du fichier
LELA__preprint_.pdf (552.32 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05445830 , version 1 (07-01-2026)

Licence

Identifiants

Citer

Samy Haffoudhi, Fabian M Suchanek, Nils Holzenberger. LELA: an LLM-based Entity Linking Approach with Zero-Shot Domain Adaptation. 2026. ⟨hal-05445830⟩
1598 Consultations
349 Téléchargements

Altmetric

Partager

  • More