Sparse Personalized Text Generation with Multi-Trajectory Reasoning

• URL: http://arxiv.org/abs/2604.24996v1
• Date: Mon, 27 Apr 2026 20:58:49 GMT
• Title: Sparse Personalized Text Generation with Multi-Trajectory Reasoning
• Abstract summary: PAT (Personalization with Aligned Trajectories) is a reasoning framework for cold-start LLM personalization.<n>It first retrieves information along two complementary trajectories: writing-style cues from stylistically similar users and topic-specific context from preference-aligned users.<n>It then employs a reinforcement learning-based, iterative dual-reasoning mechanism that enables the LLM to jointly refine and integrate these signals.
• Score: 95.19317487799292
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• Synthetic Interaction Data for Scalable Personalization in Large Language Models [67.31884245564086]
  We introduce a high-fidelity synthetic data generation framework called PersonaGym.<n>Unlike prior work that treats personalization as static persona-preference pairs, PersonaGym models a dynamic preference process.<n>We release PersonaAtlas, a large-scale, high-quality, and diverse synthetic dataset of high-fidelity multi-turn personalized interaction trajectories.
  arXiv  Detail & Related papers  (2026-02-12T20:41:22Z)
• Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs [13.018317214170727]
  Personalizing large language models (LLMs) to individual users requires incorporating extensive interaction histories and profiles.<n>Existing approaches rely on methods such as selecting recent interactions or prompting summarization models to compress user profiles.<n>We investigate whether LLMs' attention patterns can effectively identify important personalization signals for intelligent context compression.
  arXiv  Detail & Related papers  (2026-02-08T02:31:15Z)
• Reasoning-Based Personalized Generation for Users with Sparse Data [120.94029850012045]
  We introduce GraSPer, a novel framework for enhancing personalized text generation under sparse context.<n>GraSPer first augments user context by predicting items that the user would likely interact with in the future.<n>With reasoning alignment, it then generates texts for these interactions to enrich the augmented context.<n>In the end, it generates personalized outputs conditioned on both the real and synthetic histories.
  arXiv  Detail & Related papers  (2026-01-31T01:54:23Z)
• POPI: Personalizing LLMs via Optimized Natural Language Preference Inference [42.25870704040321]
  POPI is a general framework that introduces a preference inference model to distill heterogeneous user signals into concise natural language summaries.<n>These summaries act as transparent, compact, and transferable personalization representations that condition a shared generation model to produce personalized responses.<n>Extensive experiments across four personalization benchmarks demonstrate that POPI consistently improves personalization accuracy while reducing context overhead by a large margin.
  arXiv  Detail & Related papers  (2025-10-17T23:07:57Z)
• Embedding-to-Prefix: Parameter-Efficient Personalization for Pre-Trained Large Language Models [6.445337954429245]
  Large language models (LLMs) excel at generating contextually relevant content.<n>We propose Embedding-to-Prefix (E2P), a parameter-efficient method that injects context embeddings into an LLM's hidden representation space.<n>We evaluate E2P across two public datasets and in a production setting: dialogue personalization on Persona-Chat, contextual headline generation on PENS, and large-scale personalization for music and podcast consumption.
  arXiv  Detail & Related papers  (2025-05-16T13:34:25Z)
• Personalized Text Generation with Contrastive Activation Steering [63.60368120937822]
  We propose a training-free framework that disentangles and represents personalized writing style as a vector.<n>Our framework achieves a significant 8% relative improvement in personalized generation while reducing storage requirements by 1700 times over PEFT method.
  arXiv  Detail & Related papers  (2025-03-07T08:07:15Z)
• PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection [68.8373788348678]
  Visual instruction tuning adapts pre-trained Multimodal Large Language Models to follow human instructions.<n>PRISM is the first training-free framework for efficient visual instruction selection.<n>It reduces the end-to-end time for data selection and model tuning to just 30% of conventional pipelines.
  arXiv  Detail & Related papers  (2025-02-17T18:43:41Z)
• Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes [50.544186914115045]
  Large language models (LLMs) are increasingly embedded in everyday applications.<n> Ensuring their alignment with the diverse preferences of individual users has become a critical challenge.<n>We present a novel framework for few-shot steerable alignment.
  arXiv  Detail & Related papers  (2024-12-18T16:14:59Z)
• Robust Utility-Preserving Text Anonymization Based on Large Language Models [80.5266278002083]
  Anonymizing text that contains sensitive information is crucial for a wide range of applications.<n>Existing techniques face the emerging challenges of the re-identification ability of large language models.<n>We propose a framework composed of three key components: a privacy evaluator, a utility evaluator, and an optimization component.
  arXiv  Detail & Related papers  (2024-07-16T14:28:56Z)
• Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment [72.99676237703099]
  We propose a new framework that boosts the alignment of large language models with human preferences.<n>Our key idea is leveraging the human prior knowledge within the small (seed) data.<n>We introduce a noise-aware preference learning algorithm to mitigate the risk of low quality within generated preference data.
  arXiv  Detail & Related papers  (2024-06-06T18:01:02Z)
• Integrating Summarization and Retrieval for Enhanced Personalization via Large Language Models [11.950478880423733]
  Personalization is an essential factor in user experience with natural language processing (NLP) systems. With the emergence of Large Language Models (LLMs), a key question is how to leverage these models to better personalize user experiences. We propose a novel summary-augmented personalization with task-aware user summaries generated by LLMs.
  arXiv  Detail & Related papers  (2023-10-30T23:40:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.