LEAD: LLM-enhanced Engine for Author Disambiguation

TL;DR

This paper introduces LEAD, a hybrid framework combining semantic features from Large Language Models with structural network evidence to improve author disambiguation across bibliographic databases, achieving high accuracy and efficiency.

Contribution

The study presents LEAD, a novel hybrid approach that effectively integrates LLM-derived semantic features with network-based structural evidence for author disambiguation.

Findings

LEAD achieves F1 = 96.7% and accuracy = 95.7%.

Bibliographic Coupling is the fastest and strongest single-source method.

Hybrid strategies outperform individual methods in author disambiguation.

Abstract

Author Name Disambiguation (AND) is a long-standing challenge in bibliometrics and scientometrics, as name ambiguity undermines the accuracy of bibliographic databases and the reliability of research evaluation. This study addresses the problem of cross-source disambiguation by linking academic career records from CercaUniversit\`a, the official registry of Italian academics, with author profiles in Scopus. We introduce LEAD (LLM-enhanced Engine for Author Disambiguation), a novel hybrid framework that combines semantic features extracted through Large Language Models (LLMs) with structural evidence derived from co-authorship and citation networks. Using a gold standard of 606 ambiguous cases, we compare five methods: (i) Label Spreading on co-authorship networks; (ii) Bibliographic Coupling on citation networks; (iii) a standalone LLM-based approach; (iv) an LLM-enriched configuration; and (v) the proposed hybrid pipeline. LEAD achieves the best performance (F1 = 96.7%, accuracy = 95.7%) with lower computational cost than full LLM models. Bibliographic Coupling emerges as the fastest and strongest single-source method. These findings demonstrate that integrating semantic and structural signals within a selective hybrid strategy offers a robust and scalable solution to cross-database author identification. Beyond the Italian case, this work highlights the potential of hybrid LLM-based methods to improve data quality and reliability in scientometric analyses.