Towards Explainable Temporal User Profiling with LLMs

TL;DR

This paper introduces a method using large language models to create natural language summaries of user interactions, capturing temporal preferences for more accurate and explainable recommendations.

Contribution

It proposes a novel framework that models temporal user preferences with LLM-generated textual profiles, enhancing both recommendation accuracy and interpretability.

Findings

Improved recommendation performance over baseline methods

Generated natural language profiles enhance transparency

Attention mechanisms effectively fuse short-term and long-term preferences

Abstract

Accurately modeling user preferences is vital not only for improving recommendation performance but also for enhancing transparency in recommender systems. Conventional user profiling methods, such as averaging item embeddings, often overlook the evolving, nuanced nature of user interests, particularly the interplay between short-term and long-term preferences. In this work, we leverage large language models (LLMs) to generate natural language summaries of users' interaction histories, distinguishing recent behaviors from more persistent tendencies. Our framework not only models temporal user preferences but also produces natural language profiles that can be used to explain recommendations in an interpretable manner. These textual profiles are encoded via a pre-trained model, and an attention mechanism dynamically fuses the short-term and long-term embeddings into a comprehensive user representation. Beyond boosting recommendation accuracy over multiple baselines, our approach naturally supports explainability: the interpretable text summaries and attention weights can be exposed to end users, offering insights into why specific items are suggested. Experiments on real-world datasets underscore both the performance gains and the promise of generating clearer, more transparent justifications for content-based recommendations.