# PersonaFactor: Preference Factors with Dynamic Selection for LLM Personalization

arXiv: https://arxiv.org/abs/2610.16372 · HTML: https://mlsanity.com/paper/2610.16372/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 12 Oct 2026.

## Builds on (most cited first, 23 of 23)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Memory OS of AI Agent](https://mlsanity.com/paper/2506.06326/) (2025)
- [On Memory Construction and Retrieval for Personalized Conversational Agents](https://mlsanity.com/paper/2502.05589/) (2025)
- [LongLaMP: A Benchmark for Personalized Long-form Text Generation](https://mlsanity.com/paper/2407.11016/) (2024)
- [Large Language Models Empowered Personalized Web Agents](https://mlsanity.com/paper/2410.17236/) (2024)
- [PersonalLLM: Tailoring LLMs to Individual Preferences](https://mlsanity.com/paper/2409.20296/) (2024)
- [PAD: Personalized Alignment of LLMs at Decoding-Time](https://mlsanity.com/paper/2410.04070/) (2024)
- [Personalized Text Generation with Contrastive Activation Steering](https://mlsanity.com/paper/2503.05213/) (2025)
- [LaMP-QA: A Benchmark for Personalized Long-form Question Answering](https://mlsanity.com/paper/2506.00137/) (2025)
- [Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation](https://mlsanity.com/paper/2512.06690/) (2025)
- [Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward](https://mlsanity.com/paper/2504.03206/) (2025)
- [PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level Adaptation](https://mlsanity.com/paper/2503.01303/) (2025)
- [Latent Inter-User Difference Modeling for LLM Personalization](https://mlsanity.com/paper/2507.20849/) (2025)
- [PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Process](https://mlsanity.com/paper/2507.04607/) (2025)
- [Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis](https://mlsanity.com/paper/2506.01262/) (2025)
- [CoPL: Collaborative Preference Learning for Personalizing LLMs](https://mlsanity.com/paper/2503.01658/) (2025)
- [ThoughtTrace: Understanding User Thoughts in Real-World LLM Interactions](https://mlsanity.com/paper/2605.20087/) (2026)
- [RPM: Reasoning-Level Personalization for Black-Box Large Language Models](https://mlsanity.com/paper/2505.21082/) (2025)
- [CoPA: Benchmarking Personalized Question Answering with Data-Informed Cognitive Factors](https://mlsanity.com/paper/2604.14773/) (2026)

## Abstract (arXiv)

Although users may express different personalization needs across tasks, these task-specific behaviors can reflect shared underlying preference mechanisms. Existing LLM personalization methods often focus on surface-level interactions or undifferentiated histories, overlooking the shared mechanisms underlying these behaviors. We introduce PersonaFactors, a framework that distills reusable and interpretable personalization factors from heterogeneous user interactions. We construct a library of thirteen PersonaFactors by extracting evidence-grounded rationales and clustering recurring patterns across tasks, and develop a dynamic factor-guided generation framework that selects factors relevant to each user's history and current request. Across four personalization benchmarks and four backbone models, Dynamic PersonaFactor achieves the best score on every reported metric. Representation analyses further show that PersonaFactors and user history induce partially overlapping low-dimensional representations, and that their joint use yields complementary shifts. Taken together, these findings suggest that factor-based and history-based personalization can mutually reinforce each other.