CLAILGAug 26, 2024

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

arXiv:2408.14236v13 citationsh-index: 5
Originality Synthesis-oriented
AI Analysis

This work addresses ontology learning for AI systems, but it is incremental as it compares existing knowledge types without major breakthroughs.

The paper tackled type classification in ontology learning by comparing extrinsic knowledge representation (semantic towers) with intrinsic knowledge in large language models, finding a trade-off between performance and semantic grounding, with results reported on the LLMs4OL 2024 challenge.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes