TEARS: Textual Representations for Scrutable Recommendations

TL;DR

TEARS introduces natural language summaries of user preferences in recommender systems, enhancing interpretability and user control while achieving competitive performance through a hybrid model with optimal transport.

Contribution

The paper proposes TEARS, a novel method encoding user preferences as natural language summaries and aligning them with latent embeddings, improving transparency and controllability in recommendations.

Findings

Summaries effectively capture unique user preferences.

TEARS surpasses traditional VAE models in recommendation accuracy.

User editing of summaries demonstrates improved controllability.

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 a latent embedding, TEARS encodes them in natural text, providing transparency and allowing users to edit them. To do so, TEARS uses a modern LLM to generate user summaries based on user preferences. We find the summaries capture user preferences uniquely. Using these summaries, we take a hybrid approach where we use an optimal transport procedure to align the summaries' representation with the learned representation of a standard VAE for collaborative filtering. We find this approach can surpass the performance of three popular VAE models while providing user-controllable recommendations. We also analyze the controllability of TEARS through three simulated user tasks to evaluate the effectiveness of a user editing its summary.