![[2602.21219] Reasoning-Based Personalized Generation for Users with Sparse Data](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.21219] Reasoning-Based Personalized Generation for Users with Sparse Data
Summary
This article presents GraSPer, a novel framework designed to enhance personalized text generation for users with sparse data, addressing challenges in LLM personalization.
Why It Matters
As personalization becomes increasingly important in AI applications, this research addresses a critical gap for users with limited interaction histories. By improving the personalization of responses, it can significantly enhance user experience in various domains, such as e-commerce and social media.
Key Takeaways
- GraSPer augments user context by predicting future interactions.
- The framework generates personalized outputs based on both real and synthetic user histories.
- Extensive experiments show significant performance gains in personalized generation.
Computer Science > Computation and Language arXiv:2602.21219 (cs) [Submitted on 31 Jan 2026] Title:Reasoning-Based Personalized Generation for Users with Sparse Data Authors:Bo Ni, Branislav Kveton, Samyadeep Basu, Subhojyoti Mukherjee, Leyao Wang, Franck Dernoncourt, Sungchul Kim, Seunghyun Yoon, Zichao Wang, Ruiyi Zhang, Puneet Mathur, Jihyung Kil, Jiuxiang Gu, Nedim Lipka, Yu Wang, Ryan A. Rossi, Tyler Derr View a PDF of the paper titled Reasoning-Based Personalized Generation for Users with Sparse Data, by Bo Ni and 16 other authors View PDF HTML (experimental) Abstract:Large Language Model (LLM) personalization holds great promise for tailoring responses by leveraging personal context and history. However, real-world users usually possess sparse interaction histories with limited personal context, such as cold-start users in social platforms and newly registered customers in online E-commerce platforms, compromising the LLM-based personalized generation. To address this challenge, we introduce GraSPer (Graph-based Sparse Personalized Reasoning), a novel framework for enhancing personalized text generation under sparse context. GraSPer first augments user context by predicting items that the user would likely interact with in the future. With reasoning alignment, it then generates texts for these interactions to enrich the augmented context. In the end, it generates personalized outputs conditioned on both the real and synthetic histories, ensuring alignment with user ...