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

• URL: http://arxiv.org/abs/2502.19148v1
• Date: Wed, 26 Feb 2025 14:07:37 GMT
• Title: Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs
• Authors: Zhaowei Zhang, Fengshuo Bai, Qizhi Chen, Chengdong Ma, Mingzhi Wang, Haoran Sun, Zilong Zheng, Yaodong Yang,
• Abstract summary: We introduce Amulet, a training-free framework that formulates the decoding process of every token as a separate online learning problem.<n>We show that Amulet can achieve significant performance improvements in rich settings with combinations of different LLMs, datasets, and user preferences.
• Score: 28.759591573106917
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• FSPO: Few-Shot Preference Optimization of Synthetic Preference Data in LLMs Elicits Effective Personalization to Real Users [111.56469697145519]
  We propose Few-Shot Preference Optimization, which reframes reward modeling as a meta-learning problem. Under this framework, an LLM learns to quickly adapt to a user via a few labeled preferences from that user, constructing a personalized reward function for them. We generate over 1M synthetic personalized preferences using publicly available LLMs. We evaluate FSPO on personalized open-ended generation for up to 1,500 synthetic users across three domains: movie reviews, pedagogical adaptation based on educational background, and general question answering, along with a controlled human study.
  arXiv  Detail & Related papers  (2025-02-26T17:08:46Z)
• 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)
• A Systematic Examination of Preference Learning through the Lens of Instruction-Following [83.71180850955679]
  We use a novel synthetic data generation pipeline to generate 48,000 instruction unique-following prompts.<n>With our synthetic prompts, we use two preference dataset curation methods - rejection sampling (RS) and Monte Carlo Tree Search (MCTS)<n>Experiments reveal that shared prefixes in preference pairs, as generated by MCTS, provide marginal but consistent improvements.<n>High-contrast preference pairs generally outperform low-contrast pairs; however, combining both often yields the best performance.
  arXiv  Detail & Related papers  (2024-12-18T15:38:39Z)
• A CLIP-Powered Framework for Robust and Generalizable Data Selection [51.46695086779598]
  Real-world datasets often contain redundant and noisy data, imposing a negative impact on training efficiency and model performance. Data selection has shown promise in identifying the most representative samples from the entire dataset. We propose a novel CLIP-powered data selection framework that leverages multimodal information for more robust and generalizable sample selection.
  arXiv  Detail & Related papers  (2024-10-15T03:00:58Z)
• PersonalLLM: Tailoring LLMs to Individual Preferences [11.717169516971856]
  We present a public benchmark, PersonalLLM, focusing on adapting LLMs to provide maximal benefits for a particular user.<n>We curate open-ended prompts paired with many high-quality answers over which users would be expected to display heterogeneous latent preferences.<n>Our dataset and generated personalities offer an innovative testbed for developing personalization algorithms.
  arXiv  Detail & Related papers  (2024-09-30T13:55:42Z)
• Geometric-Averaged Preference Optimization for Soft Preference Labels [78.2746007085333]
  Many algorithms for aligning LLMs with human preferences assume that human preferences are binary and deterministic.<n>In this work, we introduce the distributional soft preference labels and improve Direct Preference Optimization (DPO) with a weighted geometric average of the LLM output likelihood in the loss function.
  arXiv  Detail & Related papers  (2024-09-10T17:54:28Z)
• Value Augmented Sampling for Language Model Alignment and Personalization [39.070662999014836]
  We present a new framework for reward optimization, Value Augmented Sampling (VAS) VAS solves for the optimal reward-maximizing policy without co-training the policy and the value function. Our algorithm unlocks the new capability of composing several rewards and controlling the extent of each one during deployment time.
  arXiv  Detail & Related papers  (2024-05-10T17:59:04Z)
• Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts [95.09994361995389]
  Relative Preference Optimization (RPO) is designed to discern between more and less preferred responses derived from both identical and related prompts. RPO has demonstrated a superior ability to align large language models with user preferences and to improve their adaptability during the training process.
  arXiv  Detail & Related papers  (2024-02-12T22:47:57Z)
• Linear Speedup in Personalized Collaborative Learning [69.45124829480106]
  Personalization in federated learning can improve the accuracy of a model for a user by trading off the model's bias. We formalize the personalized collaborative learning problem as optimization of a user's objective. We explore conditions under which we can optimally trade-off their bias for a reduction in variance.
  arXiv  Detail & Related papers  (2021-11-10T22:12:52Z)
• Optimizing Offer Sets in Sub-Linear Time [5.027714423258537]
  We propose an algorithm for personalized offer set optimization that runs in time sub-linear in the number of items. Our algorithm can be entirely data-driven, relying on samples of the user, where a sample' refers to the user interaction data typically collected by firms.
  arXiv  Detail & Related papers  (2020-11-17T13:02:56Z)

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.