Interpretable Recommendations and Parameter-Grounded Explanations with Multi-Graph Attention – MSI

Working Paper

Interpretable Recommendations and Parameter-Grounded Explanations with Multi-Graph Attention

Yan Leng, Xiao Liu and Rodrigo Ruiz

Feb 4, 2026

Download

Develops an explanation-integrated framework for recommendation systems in which prediction and explanation rely on the same internal signals to deliver interpretable predictions and user-centered explanations.

Topics

research recap

Engineering Recommender Systems for Transparency and Trust

As AI-assisted search and service interactions become ubiquitous, recommender systems must demonstrate the transparency needed to persuade customers and earn their trust. This approach shows how to engineer such systems to deliver interpretable predictions and user-centered explanations that are grounded in the same quality and social signals used for prediction.

By using MSI.org you agree to our use of cookies as identifiers and for other features of the site as described in our Privacy Policy.