Rethink the Evaluation Protocol of Model Merging on Classification Task

Model merging combines multiple fine-tuned models into a single one via parameter fusion, achieving improvements across many tasks. However, in the classification task, we find a misalignment issue between merging outputs and the fine-tuned classifier, which limits its effectiveness. In this paper,...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-12
Hauptverfasser:	Kong, Fanshuang, Zhang, Richong, Nie, Zhijie, Wang, Ziqiao
Format:	Artikel
Sprache:	eng
Schlagworte:	Classification Effectiveness Misalignment Performance evaluation
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!