用大模型零样本实现学术知识图谱实体链接，支持新型会议实体
DBLPLink 2.0 -- An Entity Linker for the DBLP Scholarly Knowledge Graph
- 基于大模型输出概率进行候选实体重排序
- 无需训练即可处理新引入的会议实体类型
- 适合需要快速适配新数据的学术知识图谱构建者
本文提出DBLPLink 2.0，一个针对DBLP 2025版基于RDF的知识图谱的实体链接系统。相比2022版本，当前版本将出版物会议（publication venues）作为新实体类型dblpl:Stream。此前的DBLPLink通过训练知识图谱嵌入和重排序器生成链接；而本工作采用零样本方法，利用大语言模型（LLM）在倒数第二层输出的"yes" token对候选实体进行重排序，无需额外训练即可完成链接。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。