Spectral Souping: A Unified Framework for Online Preference Alignment

• URL: http://arxiv.org/abs/2605.20408v1
• Date: Tue, 19 May 2026 19:04:47 GMT
• Title: Spectral Souping: A Unified Framework for Online Preference Alignment
• Abstract summary: Reinforcement Learning from Human Feedback (RLHF) effectively aligns Large Language Models with aggregate human preferences but often fails to address the diverse and conflicting needs of individual users.<n>We introduce Spectral Souping, a unified framework for efficient, online preference alignment.<n> Experiments on online preference alignment benchmarks demonstrate that our method achieves significant performance improvements over existing state-of-the-art approaches.
• Score: 39.263620139543505
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement Learning from Human Feedback (RLHF) effectively aligns Large Language Models (LLMs) with aggregate human preferences but often fails to address the diverse and conflicting needs of individual users. To overcome this issue, we introduce Spectral Souping, a unified framework for efficient, online preference alignment. Our contribution is the discovery of a universal spectral representation within LLMs, which is proven to be highly amenable to model merging. This theoretical insight enables a two-phase methodology: we first learn a basis of specialized policies offline, each focused on a distinct, fine-grained preference dimension. An online adaptation algorithm then efficiently ``soups'' these policies at inference time, either by merging their outputs or parameters, enabling rapid model adaptation without the need for costly online retraining w.r.t. tailored preference rewards. Experiments on online preference alignment benchmarks demonstrate that our method achieves significant performance improvements over existing state-of-the-art approaches, presenting a scalable and computationally efficient solution for dynamically adapting LLMs to individual user preferences.

Related papers

• FedPDPO: Federated Personalized Direct Preference Optimization for Large Language Model Alignment [55.97027207627]
  Fed PDPO (Federated Personalized Direct Preference Optimization) is a personalized framework for preference alignment of large language models (LLMs)<n>It adopts a parameter-efficient fine-tuning architecture where each client maintains a frozen pretrained LLM backbone augmented with a Low-Rank Adaptation (LoRA) adapter, enabling communication-efficient aggregation.<n>Experiments on multiple preference datasets demonstrate state-of-the-art performance, achieving up to 4.80% average accuracy improvements in federated intra-domain and cross-domain settings.
  arXiv  Detail & Related papers  (2026-03-20T08:24:49Z)
• Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization [37.54165341391688]
  We introduce a novel problem: Sample Scheduling for DPO.<n>We propose SamS, an efficient and effective algorithm that adaptively selects samples in each training batch.<n>This work points to a promising new direction for improving LLM alignment through batch-wise sample selection.
  arXiv  Detail & Related papers  (2025-06-08T10:26:09Z)
• Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment [24.419502686973495]
  We introduce a flexible paradigm for individual preference alignment.<n>We validate our approach across multiple text generation tasks and demonstrate that it can produce aligned quality as well as or better than PEFT-based methods.
  arXiv  Detail & Related papers  (2024-12-30T09:58:31Z)
• 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)
• Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness [27.43137305486112]
  We propose a novel Self-supervised Preference Optimization (SPO) framework, which constructs a self-supervised preference degree loss combined with the alignment loss. The results demonstrate that SPO can be seamlessly integrated with existing preference optimization methods to achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-09-26T12:37:26Z)
• SAIL: Self-Improving Efficient Online Alignment of Large Language Models [56.59644677997827]
  Reinforcement Learning from Human Feedback is a key method for aligning large language models with human preferences. Recent literature has focused on designing online RLHF methods but still lacks a unified conceptual formulation. Our approach significantly improves alignment performance on open-sourced datasets with minimal computational overhead.
  arXiv  Detail & Related papers  (2024-06-21T18:05:35Z)
• Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment [58.049113055986375]
  We develop a single stage approach named Alignment with Integrated Human Feedback (AIHF) to train reward models and the policy.<n>The proposed approach admits a suite of efficient algorithms, which can easily reduce to, and leverage, popular alignment algorithms.<n>We demonstrate the efficiency of the proposed solutions with extensive experiments involving alignment problems in LLMs and robotic control problems in MuJoCo.
  arXiv  Detail & Related papers  (2024-06-11T01:20:53Z)
• Unified Preference Optimization: Language Model Alignment Beyond the Preference Frontier [0.5120567378386615]
  We propose a unified approach to aligning large language models (LLMs)<n>Based on a simple decomposition of preference and auxiliary objectives, we allow for tuning LLMs to optimize user and designer preferences.
  arXiv  Detail & Related papers  (2024-05-28T08:35:48Z)
• Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback [70.32795295142648]
  Linear alignment is a novel algorithm that aligns language models with human preferences in one single inference step. Experiments on both general and personalized preference datasets demonstrate that linear alignment significantly enhances the performance and efficiency of LLM alignment.
  arXiv  Detail & Related papers  (2024-01-21T10:46:23Z)

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.