# Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs

arXiv: https://arxiv.org/abs/2502.19148 · HTML: https://mlsanity.com/paper/2502.19148/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 67 references that are in the map.
- First posted on arXiv 26 Feb 2025.

## Builds on (most cited first, 30 of 46)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [Introduction to Online Convex Optimization](https://mlsanity.com/paper/1909.05207/) (2019)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [RewardBench: Evaluating Reward Models for Language Modeling](https://mlsanity.com/paper/2403.13787/) (2024)
- [Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts](https://mlsanity.com/paper/2406.12845/) (2024)
- [CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning](https://mlsanity.com/paper/2207.01780/) (2022)
- [Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking](https://mlsanity.com/paper/2403.09629/) (2024)
- [Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models](https://mlsanity.com/paper/2408.00724/) (2024)
- [AI Alignment: A Comprehensive Survey](https://mlsanity.com/paper/2310.19852/) (2023)
- [The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning](https://mlsanity.com/paper/2312.01552/) (2023)
- [Foundational Challenges in Assuring Alignment and Safety of Large Language Models](https://mlsanity.com/paper/2404.09932/) (2024)
- [RAIN: Your Language Models Can Align Themselves without Finetuning](https://mlsanity.com/paper/2309.07124/) (2023)
- [HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM](https://mlsanity.com/paper/2311.09528/) (2023)
- [Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling](https://mlsanity.com/paper/2502.06703/) (2025)
- [SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agents](https://mlsanity.com/paper/2403.08715/) (2024)
- [When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities](https://mlsanity.com/paper/2307.16376/) (2023)
- [Tuning Language Models by Proxy](https://mlsanity.com/paper/2401.08565/) (2024)
- [Panacea: Pareto Alignment via Preference Adaptation for LLMs](https://mlsanity.com/paper/2402.02030/) (2024)
- [Decoding-time Realignment of Language Models](https://mlsanity.com/paper/2402.02992/) (2024)

## Built on by (most cited first, 29 of 29)

- [Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)](https://mlsanity.com/paper/2505.16394/) (2025)
- [Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space](https://mlsanity.com/paper/2505.13308/) (2025)
- [A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications](https://mlsanity.com/paper/2503.17003/) (2025)
- [Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation](https://mlsanity.com/paper/2512.06690/) (2025)
- [A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models](https://mlsanity.com/paper/2504.07070/) (2025)
- [Coarse-to-Fine Grounded Memory for LLM Agent Planning](https://mlsanity.com/paper/2508.15305/) (2025)
- [Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions](https://mlsanity.com/paper/2602.22680/) (2026)
- [CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering](https://mlsanity.com/paper/2507.04756/) (2025)
- [LLM-Auction: Generative Auction towards LLM-Native Advertising](https://mlsanity.com/paper/2512.10551/) (2025)
- [Self-Guided Function Calling in Large Language Models via Stepwise Experience Recall](https://mlsanity.com/paper/2508.15214/) (2025)
- [T-POP: Test-Time Personalization with Online Preference Feedback](https://mlsanity.com/paper/2509.24696/) (2025)
- [FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Data](https://mlsanity.com/paper/2508.04698/) (2025)
- [Inference-Time Personalized Alignment with a Few User Preference Queries](https://mlsanity.com/paper/2511.02966/) (2025)
- [SpecSteer: Synergizing Local Context and Global Reasoning for Efficient Personalized Generation](https://mlsanity.com/paper/2603.16219/) (2026)
- [EXACT: Explicit Attribute-Guided Decoding-Time Personalization](https://mlsanity.com/paper/2602.17695/) (2026)
- [CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation](https://mlsanity.com/paper/2601.06352/) (2026)
- [When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs](https://mlsanity.com/paper/2601.11000/) (2026)
- [PoliCon: Evaluating LLMs on Achieving Diverse Political Consensus Objectives](https://mlsanity.com/paper/2505.19558/) (2025)
- [PILA: Plug-and-Play Insertion for LLM-native Advertising](https://mlsanity.com/paper/2607.25590/) (2026)
- [Alignment-Aware Decoding](https://mlsanity.com/paper/2509.26169/) (2025)
- [PrefReward: Learning User Preference Matrix for Personalized Text Generation](https://mlsanity.com/paper/2607.21067/) (2026)
- [MAVIS: Multi-Objective Alignment via Inference-Time Value-Guided Selection](https://mlsanity.com/paper/2508.13415/) (2025)
- [Pref-CTRL: Preference Driven LLM Alignment using Representation Editing](https://mlsanity.com/paper/2604.23543/) (2026)
- [MATO: Multi-objective Personalized Alignment with Test-time Optimization for Large Language Models](https://mlsanity.com/paper/2605.25342/) (2026)
- [REAR: Test-time Preference Realignment through Reward Decomposition](https://mlsanity.com/paper/2606.30339/) (2026)
- [Automatic Hard Example Synthesis with Multi-Level Agentic Data Curation](https://mlsanity.com/paper/2607.14256/) (2026)
- [Personalizing Large Language Model Agents with Small Policy Models](https://mlsanity.com/paper/2608.00215/) (2026)
- [GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning](https://mlsanity.com/paper/2608.02585/) (2026)
- [HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization](https://mlsanity.com/paper/2609.09835/) (2026)

## Abstract (arXiv)

How to align large language models (LLMs) with user preferences from a static general dataset has been frequently studied. However, user preferences are usually personalized, changing, and diverse regarding culture, values, or time. This leads to the problem that the actual user preferences often do not coincide with those trained by the model developers in the practical use of LLMs. Since we cannot collect enough data and retrain for every demand, researching efficient real-time preference adaptation methods based on the backbone LLMs during test time is important. To this end, we introduce Amulet, a novel, training-free framework that formulates the decoding process of every token as a separate online learning problem with the guidance of simple user-provided prompts, thus enabling real-time optimization to satisfy users' personalized preferences. To reduce the computational cost brought by this optimization process for each token, we additionally provide a closed-form solution for each iteration step of the optimization process, thereby reducing the computational time cost to a negligible level. The detailed experimental results demonstrate that Amulet can achieve significant performance improvements in rich settings with combinations of different LLMs, datasets, and user preferences, while maintaining acceptable computational efficiency.