Evaluating Recabilities of Foundation Models: A Multi-Domain, Multi-Dataset Benchmark

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Qijiong, Zhu, Jieming, Lai, Yingxin, Dong, Xiaoyu, Fan, Lu, Bian, Zhipeng, Dong, Zhenhua, Wu, Xiao-Ming
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916925058056192
author Liu, Qijiong
Zhu, Jieming
Lai, Yingxin
Dong, Xiaoyu
Fan, Lu
Bian, Zhipeng
Dong, Zhenhua
Wu, Xiao-Ming
author_facet Liu, Qijiong
Zhu, Jieming
Lai, Yingxin
Dong, Xiaoyu
Fan, Lu
Bian, Zhipeng
Dong, Zhenhua
Wu, Xiao-Ming
contents Comprehensive evaluation of the recommendation capabilities of existing foundation models across diverse datasets and domains is essential for advancing the development of recommendation foundation models. In this study, we introduce RecBench-MD, a novel and comprehensive benchmark designed to assess the recommendation abilities of foundation models from a zero-resource, multi-dataset, and multi-domain perspective. Through extensive evaluations of 19 foundation models across 15 datasets spanning 10 diverse domains -- including e-commerce, entertainment, and social media -- we identify key characteristics of these models in recommendation tasks. Our findings suggest that in-domain fine-tuning achieves optimal performance, while cross-dataset transfer learning provides effective practical support for new recommendation scenarios. Additionally, we observe that multi-domain training significantly enhances the adaptability of foundation models. All code and data have been publicly released to facilitate future research.
format Preprint
id arxiv_https___arxiv_org_abs_2508_21354
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evaluating Recabilities of Foundation Models: A Multi-Domain, Multi-Dataset Benchmark
Liu, Qijiong
Zhu, Jieming
Lai, Yingxin
Dong, Xiaoyu
Fan, Lu
Bian, Zhipeng
Dong, Zhenhua
Wu, Xiao-Ming
Information Retrieval
Comprehensive evaluation of the recommendation capabilities of existing foundation models across diverse datasets and domains is essential for advancing the development of recommendation foundation models. In this study, we introduce RecBench-MD, a novel and comprehensive benchmark designed to assess the recommendation abilities of foundation models from a zero-resource, multi-dataset, and multi-domain perspective. Through extensive evaluations of 19 foundation models across 15 datasets spanning 10 diverse domains -- including e-commerce, entertainment, and social media -- we identify key characteristics of these models in recommendation tasks. Our findings suggest that in-domain fine-tuning achieves optimal performance, while cross-dataset transfer learning provides effective practical support for new recommendation scenarios. Additionally, we observe that multi-domain training significantly enhances the adaptability of foundation models. All code and data have been publicly released to facilitate future research.
title Evaluating Recabilities of Foundation Models: A Multi-Domain, Multi-Dataset Benchmark
topic Information Retrieval
url https://arxiv.org/abs/2508.21354