Sparse Personalized Text Generation with Multi-Trajectory Reasoning

TL;DR

The paper introduces PAT, a reasoning framework that enhances cold-start personalization in large language models by retrieving and integrating style and topic signals through iterative reinforcement learning.

Contribution

It proposes a novel dual-trajectory reasoning method that effectively leverages heterogeneous external signals for personalization with sparse data.

Findings

PAT improves generation quality in cold-start scenarios.

Experimental results show consistent enhancement over existing methods.

The framework effectively combines style and topic cues for better personalization.

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.