analiza aiqbench
This research addresses the cold-start problem in Large Language Models by introducing GraSPer, a framework that synthesizes synthetic interaction histories to enhance personalization when user data is sparse. By leveraging graph-based reasoning and future item prediction, the method effectively enriches context without requiring extensive prior training data from new users. The approach demonstrates significant performance gains on benchmark datasets, offering a practical solution for deploying personalized AI in scenarios with limited historical records.
Reasoning-Based Personalized Generation for Users with Sparse Data
arXiv:2602.21219v2 Announce Type: replace 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 style and preferences. Extensive experiments on three benchmark personalized generation datasets show that GraSPer achieves significant performance gain, substantially improving personalization in sparse user context settings.
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
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 style and preferences. Extensive experiments on three benchmark personalized generation datasets show that GraSPer achieves significant performance gain, substantially improving personalization in sparse user context settings.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
arXiv:2602.21219 [cs.CL]
(or arXiv:2602.21219v2 [cs.CL] for this version)
Text integral sub licența deschisă a publicației · 199 cuvinte
Subiecte conexe
[AINews] not much happened today
Latent Space · 3 oct. 2026
Links #5: 2026/07
LessWrong · 31 iul. 2026
Introducing the Third Generation of Apple’s Foundation Models
Apple · 8 iun. 2026
What's Continual Learning, and Why Might We Expect To See It In Advanced LLM Agents?
LessWrong · 12 iun. 2026