作者位次 #4/5SIGIR 2026Oral· Information Retrieval (TOIS)
Understanding Internal Representations of Recommendation Models with Sparse Autoencoders
Jiayin Wang · Xiaoyu Zhang · Weizhi Ma · Zhiqiang Guo · Min Zhang
摘要
Recommendation model interpretation aims to reveal the relationships between inputs, model internal representations, and outputs to enhance the transparency, interpretability, and trustworthiness of recommendation systems. However, the inherent complexity and opacity of deep learning models pose...