English

Sparse Personalized Text Generation with Multi-Trajectory Reasoning

Artificial Intelligence 2026-04-29 v1

Abstract

As Large Language Models (LLMs) advance, personalization has become a key mechanism for tailoring outputs to individual user needs. However, most existing methods rely heavily on dense interaction histories, making them ineffective in cold-start scenarios where such data is sparse or unavailable. While external signals (e.g., content of similar users) can offer a potential remedy, leveraging them effectively remains challenging: raw context is often noisy, and existing methods struggle to reason over heterogeneous data sources. To address these issues, we introduce PAT (Personalization with Aligned Trajectories), a reasoning framework for cold-start LLM personalization. PAT first retrieves information along two complementary trajectories: writing-style cues from stylistically similar users and topic-specific context from preference-aligned users. It then employs a reinforcement learning-based, iterative dual-reasoning mechanism that enables the LLM to jointly refine and integrate these signals. Experimental results across real-world personalization benchmarks show that PAT consistently improves generation quality and alignment under sparse-data conditions, establishing a strong solution to the cold-start personalization problem.

Keywords

Cite

@article{arxiv.2604.24996,
  title  = {Sparse Personalized Text Generation with Multi-Trajectory Reasoning},
  author = {Bo Ni and Haowei Fu and Qinwen Ge and Franck Dernoncourt and Samyadeep Basu and Nedim Lipka and Seunghyun Yoon and Yu Wang and Nesreen K. Ahmed and Subhojyoti Mukherjee and Puneet Mathur and Ryan A. Rossi and Tyler Derr},
  journal= {arXiv preprint arXiv:2604.24996},
  year   = {2026}
}
R2 v1 2026-07-01T12:38:08.574Z