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

TL;DR

This paper introduces DBLPLink 2.0, a zero-shot entity linker leveraging large language models to improve linking accuracy in the updated DBLP scholarly knowledge graph, especially with new entity types.

Contribution

It presents a novel zero-shot entity linking method using LLMs and log-probability re-ranking, replacing previous KG-embedding approaches.

Findings

Effective zero-shot linking with LLMs demonstrated

Improved accuracy over previous methods

Handles new entity types like dblp:Stream

Abstract

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.