Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Bridging Textual Profiles and Latent User Embeddings for Personalization

About

Personalized systems rely on user representations to connect behavioral history with downstream recommendation applications. Existing methods typically employ either supervised latent user embeddings, which are effective for retrieval but difficult to interpret, or textual user profiles, which are interpretable but challenging to optimize for downstream utility due to lack of direct supervision. To bridge this gap, we present BLUE, a reinforcement learning framework that unifies these two forms of user representation by aligning language-based user profiles with embedding-based recommendation objectives. Given a user interaction history, BLUE leverages a profiler Large Language Model (LLM) to generate textual profiles, while an embedding model provides reward signals. This encourages the resulting textual representations to move closer to positive items and farther from negative ones in the embedding space. We further introduce a text-space supervision signal based on next-item prediction, ensuring the learned profiles remain both semantically meaningful and highly effective for downstream retrieval. Experiments on Amazon Reviews 2023 and Google Local Reviews in zero-shot sequential recommendation settings demonstrate that BLUE consistently outperforms strong baselines under both frozen and trainable embedding conditions. Notably, BLUE achieves clear gains in cross-domain transfer, highlighting the strong generalization ability of the learned user profiles. Furthermore, these generated profiles provide superior personalized context for question answering compared to raw user histories or alternative profile optimization methods. Overall, these results show that BLUE provides an effective way to unify interpretable textual profiling with discriminative latent embeddings for personalization.

Zhaoxuan Tan, Xiang Zhai, Yan Zhu, Meng Jiang, Mohamed Hammad• 2026

Related benchmarks

TaskDatasetResultRank
Sequential RecommendationAmazon Sports
NDCG@1026.2
58
Sequential RecommendationAmazon Books
NDCG@1042.3
33
Rating PredictionAmazonBook
MAE0.867
27
Sequential RecommendationGoogle Reviews
NDCG@1030.8
20
Next-item predictionAmazon Clothing
Accuracy55.7
12
Next-item predictionAmazon Books
Accuracy66.9
12
Next-item predictionAmazon Electronics
Accuracy54.5
12
Next-item predictionAmazon Sports
Accuracy59.2
12
Next-item predictionGoogle Reviews
Accuracy51
12
Rating PredictionAmazon Clothing
MAE1.02
12
Showing 10 of 19 rows

Other info

Follow for update