# Towards Explainable Temporal User Profiling with LLMs

arXiv: https://arxiv.org/abs/2505.00886 · HTML: https://mlsanity.com/paper/2505.00886/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 1 May 2025.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [KGAT: Knowledge Graph Attention Network for Recommendation](https://mlsanity.com/paper/1905.07854/) (2019)
- [Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders](https://mlsanity.com/paper/2403.03952/) (2024)
- [Explainable Recommendation: A Survey and New Perspectives](https://mlsanity.com/paper/1804.11192/) (2018)
- [A Survey on Knowledge Graph-Based Recommender Systems](https://mlsanity.com/paper/2003.00911/) (2020)
- [Improved Recurrent Neural Networks for Session-based Recommendations](https://mlsanity.com/paper/1606.08117/) (2016)
- [XRec: Large Language Models for Explainable Recommendation](https://mlsanity.com/paper/2406.02377/) (2024)
- [Zero-shot Item-based Recommendation via Multi-task Product Knowledge Graph Pre-Training](https://mlsanity.com/paper/2305.07633/) (2023)
- [LLM-Powered Explanations: Unraveling Recommendations Through Subgraph Reasoning](https://mlsanity.com/paper/2406.15859/) (2024)
- [Is More Always Better? The Effects of Personal Characteristics and Level of Detail on the Perception of Explanations in a Recommender System](https://mlsanity.com/paper/2304.00969/) (2023)

## Built on by (most cited first, 6 of 6)

- [Conf-Profile: A Confidence-Driven Reasoning Paradigm for Label-Free User Profiling](https://mlsanity.com/paper/2509.18864/) (2025)
- [Music Recommendation with Large Language Models: Challenges, Opportunities, and Evaluation](https://mlsanity.com/paper/2511.16478/) (2025)
- [StreamProfileBench: A Benchmark for Fine-Grained User Profile Inference in Real-World Streaming Scenarios](https://mlsanity.com/paper/2605.25758/) (2026)
- [Descriptive History Representations: Learning Representations by Answering Questions](https://mlsanity.com/paper/2506.02125/) (2025)
- [SPARK: Search Personalization via Agent-Driven Retrieval and Knowledge-sharing](https://mlsanity.com/paper/2512.24008/) (2025)
- [UserGPT Technical Report](https://mlsanity.com/paper/2605.08766/) (2026)

## Abstract (arXiv)

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.