This paper presents LLM4ES, a novel framework that exploits large pre-trained language models (LLMs) to derive user embeddings from event sequences. Event sequences are transformed into a textual representation, which is subsequently used to fine-tune an LLM through next-token prediction to generate high-quality embeddings. We introduce a text enrichment technique that enhances LLM adaptation to event sequence data, improving representation quality for low-variability domains. Experimental results demonstrate that LLM4ES achieves state-of-the-art performance in user classification tasks in financial and other domains, outperforming existing embedding methods. The resulting user embeddings can be incorporated into a wide range of applications, from user segmentation in finance to patient outcome prediction in healthcare.
@article{arxiv.2508.05688,
title = {LLM4ES: Learning User Embeddings from Event Sequences via Large Language Models},
author = {Aleksei Shestov and Omar Zoloev and Maksim Makarenko and Mikhail Orlov and Egor Fadeev and Ivan Kireev and Andrey Savchenko},
journal= {arXiv preprint arXiv:2508.05688},
year = {2025}
}