CLJan 8

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

arXiv:2601.05192v12 citationsh-index: 4
Originality Incremental advance
AI Analysis

This addresses entity linking for tasks like knowledge graph construction, offering a zero-shot domain adaptation method that is incremental in leveraging LLMs.

The paper tackled entity linking by proposing LELA, a modular coarse-to-fine approach using large language models that works across domains without fine-tuning, achieving competitive performance with fine-tuned methods and substantially outperforming non-fine-tuned ones.

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.

Foundations

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

Your Notes