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