What Do LLM Judges Evaluate in Recommendation Assessment? Disentangling Relevance, Local Diversity, and System-Level Diversity
IEEE Transactions on Knowledge and Data Engineering · 2026-12 · 38 (12) · 8591-8603
DOI: 10.1109/tkde.2026.3736381 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2026-12. Verfasst von Yunan Zhang und 2 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Gefördert von: Graduate Student Innovation Fund of Hebei University of Architecture.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- Graduate Student Innovation Fund of Hebei University of Architecture
Zitieren
APA
Zhang, Y., Fan, J., & Liu, Y. (2026). What Do LLM Judges Evaluate in Recommendation Assessment? Disentangling Relevance, Local Diversity, and System-Level Diversity. IEEE Transactions on Knowledge and Data Engineering, 38(12), 8591-8603. https://doi.org/10.1109/tkde.2026.3736381
Vancouver
Zhang Y, Fan J, Liu Y. What Do LLM Judges Evaluate in Recommendation Assessment? Disentangling Relevance, Local Diversity, and System-Level Diversity. IEEE Transactions on Knowledge and Data Engineering. 2026;38(12):8591-8603. doi:10.1109/tkde.2026.3736381
BibTeX
@article{Zhang2026,
author = {Zhang, Yunan and Fan, Jingjing and Liu, Yanxiao},
title = {What Do LLM Judges Evaluate in Recommendation Assessment? Disentangling Relevance, Local Diversity, and System-Level Diversity},
journal = {IEEE Transactions on Knowledge and Data Engineering},
year = {2026},
volume = {38},
number = {12},
pages = {8591--8603},
doi = {10.1109/tkde.2026.3736381}
}
EUVIMED