# CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation

arXiv: https://arxiv.org/abs/2601.06352 · HTML: https://mlsanity.com/paper/2601.06352/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 34 of its 50 references that are in the map.
- First posted on arXiv 9 Jan 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 30 of 34)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks](https://mlsanity.com/paper/2110.07602/) (2021)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Social Simulacra: Creating Populated Prototypes for Social Computing Systems](https://mlsanity.com/paper/2208.04024/) (2022)
- [Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging](https://mlsanity.com/paper/2310.11564/) (2023)
- [Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization](https://mlsanity.com/paper/2406.00045/) (2024)
- [Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation](https://mlsanity.com/paper/2404.05970/) (2024)
- [LongLaMP: A Benchmark for Personalized Long-form Text Generation](https://mlsanity.com/paper/2407.11016/) (2024)
- [Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers](https://mlsanity.com/paper/2311.09180/) (2023)
- [RAG vs Fine-tuning: Pipelines, Tradeoffs, and a Case Study on Agriculture](https://mlsanity.com/paper/2401.08406/) (2024)
- [Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model](https://mlsanity.com/paper/2310.09520/) (2023)
- [Aligning LLM Agents by Learning Latent Preference from User Edits](https://mlsanity.com/paper/2404.15269/) (2024)
- [HYDRA: Model Factorization Framework for Black-Box LLM Personalization](https://mlsanity.com/paper/2406.02888/) (2024)
- [Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalization](https://mlsanity.com/paper/2503.02450/) (2025)
- [Personalized Large Language Models](https://mlsanity.com/paper/2402.09269/) (2024)
- [Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement](https://mlsanity.com/paper/2204.13074/) (2022)
- [Personalized Text Generation with Contrastive Activation Steering](https://mlsanity.com/paper/2503.05213/) (2025)
- [Personalized LLM Response Generation with Parameterized Memory Injection](https://mlsanity.com/paper/2404.03565/) (2024)
- [Customizing Language Models with Instance-wise LoRA for Sequential Recommendation](https://mlsanity.com/paper/2408.10159/) (2024)
- [Language Model Personalization via Reward Factorization](https://mlsanity.com/paper/2503.06358/) (2025)
- [Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs](https://mlsanity.com/paper/2502.19148/) (2025)
- [PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level Adaptation](https://mlsanity.com/paper/2503.01303/) (2025)
- [Personalized LoRA for Human-Centered Text Understanding](https://mlsanity.com/paper/2403.06208/) (2024)

## Built on by (most cited first, 3 of 3)

- [Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions](https://mlsanity.com/paper/2602.22680/) (2026)
- [Do Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMs](https://mlsanity.com/paper/2601.06362/) (2026)
- [Personalize at Test Time: Learning User Preferences for Image Generation](https://mlsanity.com/paper/2610.09015/) (2026)

## Abstract (arXiv)

Adapting large language models to individual users remains challenging due to the tension between fine-grained personalization and scalable deployment. We present CARD, a hierarchical framework that achieves effective personalization through progressive refinement. CARD first clusters users according to shared stylistic patterns and learns group-specific LoRA adapters, enabling robust generalization and strong low-resource performance. To capture individual differences within each cluster, we propose an implicit preference learning mechanism that contrasts user-authored text with cluster-level generations, allowing the model to infer user-specific style preferences without manual annotation. At inference time, CARD injects personalization exclusively at decoding via lightweight user preference vectors and low-rank logit corrections, while keeping the base model frozen. Experiments on the LaMP and LongLaMP benchmarks show that CARD achieves superior generation quality compared to baselines, while significantly improving efficiency and scalability for practical personalized text generation.