Select, Don't Train: The Benefits of Modular Entity Disambiguation with LLM-Based Selection
Source
Fina Polat, Daniel Daza, Pengyu Zhang, Klim Zaporojets, Paul Groth
Author
Fina Polat, Daniel Daza, Pengyu Zhang, Klim Zaporojets, Paul Groth
Date
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
Why it matters
Suggests the trained dual-encoder can leave entity linking pipelines: with a capable LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition → doing final selection, BM25 or web search candidates suffice, and nothing needs retraining as the knowledge graph changes.
articleAn Ontology-Guided, Deduplication-Aware Extraction Layer for Knowledge Graph Construction from Heterogeneous DocumentsVaibhav Dangaich, Kevin Lewis, Kundeshwar Pundalik
articleA decodability criterion predicts when hidden-state selection beats majority voting in large language modelsZhixiang wang, Ziliang Hong, Ulas Bagci
articleBeyond FLOPs: Energy-Aware Knowledge Distillation for Sustainable LLMs on Code-Related TaskEnrique Barba Roque, Lu\'is Cruz, Annibale Panichella