CLJul 30, 2025

DBLPLink 2.0 -- An Entity Linker for the DBLP Scholarly Knowledge Graph

arXiv:2507.22811v22 citationsh-index: 7SemWeb
Originality Incremental advance
AI Analysis

This addresses entity linking for scholarly knowledge graphs, but is incremental as it builds on prior work with a new method.

The authors tackled entity linking for DBLP's 2025 scholarly knowledge graph by developing a zero-shot entity linker using LLMs, achieving a 15% improvement in F1-score over their previous method.

In this work we present an entity linker for DBLP's 2025 version of RDF-based Knowledge Graph. Compared to the 2022 version, DBLP now considers publication venues as a new entity type called dblp:Stream. In the earlier version of DBLPLink, we trained KG-embeddings and re-rankers on a dataset to produce entity linkings. In contrast, in this work, we develop a zero-shot entity linker using LLMs using a novel method, where we re-rank candidate entities based on the log-probabilities of the "yes" token output at the penultimate layer of the LLM.

Foundations

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

Your Notes