DSTI at LLMs4OL 2024 Task A: Intrinsic versus extrinsic knowledge for type classification - Archive ouverte HAL
Communication Dans Un Congrès Année : 2024

DSTI at LLMs4OL 2024 Task A: Intrinsic versus extrinsic knowledge for type classification

Résumé

We introduce semantic towers, an extrinsic knowledge representation method, and compare it to intrinsic knowledge in large language models for ontology learning. Our experiments show a trade-off between performance and semantic grounding for extrinsic knowledge compared to a fine-tuned model intrinsic knowledge. We report our findings on the Large Language Models for Ontology Learning (LLMs4OL) 2024 challenge.
Fichier principal
Vignette du fichier
mftyqchyndyhkfnqjmnfwhxbfvzgcbbh.pdf (226.18 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04678365 , version 1 (27-08-2024)

Identifiants

Citer

Hanna Abi Akl. DSTI at LLMs4OL 2024 Task A: Intrinsic versus extrinsic knowledge for type classification. 1st LLMs4OL Challenge @ ISWC 2024, Nov 2024, Maryland / USA, United States. ⟨hal-04678365⟩
39 Consultations
10 Téléchargements

Altmetric

Partager

More