TEARS: Text Representations for Scrutable Recommendations

Emiliano Penaloza, Olivier Gouvert, Haolun Wu, Laurent Charlin

Track: User modeling, personalization and recommendation

Keywords: Recommender Systems, Large language models, Interpretable AI, Scutable models

Abstract:

Traditional recommender systems rely on high-dimensional (latent)
embeddings for modeling user-item interactions, often resulting in
opaque representations that lack interpretability. Moreover, these
systems offer limited control to users over their recommendations.
Inspired by recent work, we introduce TExtuAl Representations for
Scrutable recommendations (TEARS) to address these challenges.
Instead of representing a user’s interests through latent embed-
dings, TEARS encodes them in natural text, providing transparency
and allowing users to edit them. To encode such preferences, we
use modern LLMs to generate high-quality user summaries which
we find uniquely capture user preferences. Using these summaries
we take a hybrid approach where we use an optimal transport
procedure to align the summaries’ representations with the repre-
sentation of a standard VAE for collaborative filtering. We find this
approach can surpass the performance of the three popular VAE
models while providing user-controllable recommendations. We
further analyze the controllability of TEARS through three simu-
lated user tasks to evaluate the effectiveness of user edits on their
summaries. Our code and all user-summaries can be seen in an
anonymized repository.

Submission Number: 955