UniARM: Towards a Unified Autoregressive Reward Model for Multi-Objective Test-Time Alignment

• URL: http://arxiv.org/abs/2602.09538v1
• Date: Tue, 10 Feb 2026 08:49:28 GMT
• Title: UniARM: Towards a Unified Autoregressive Reward Model for Multi-Objective Test-Time Alignment
• Abstract summary: We propose Preference-Modulated & Shared Low-Rank Adaptation (MoSLoRA) for ARM training.<n>MoSLoRA mitigates feature entanglement and enables precise control over preference trade-offs during inference.<n>We introduce the Unified Autoregressive Reward Model (UniARM), a novel framework for multi-objective test-time alignment.
• Score: 30.711521764097657
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-objective alignment aims to align LLM responses with multiple human preference objectives. Among existing methods, guiding the generation of frozen LLMs through autoregressive reward models (ARMs) to accomplish multi-objective test-time alignment is a low-cost solution. However, these methods typically rely on independent parameters for each preference objective, either by training ARMs independently across preference dimensions, which neglects interactions among preference features, or by training a single ARM with separate feature extraction modules for each preference, which can cause feature entanglement. Both strategies can result in misalignment between generated outputs and user preferences. To address this limitation, we propose Preference-Modulated \& Shared Low-Rank Adaptation (MoSLoRA) for ARM training, which first extracts shared features via a preference-agnostic module and then applies affine transformations to shared features via a preference modulation module conditioned on mixed preference vectors. This design mitigates feature entanglement and enables precise control over preference trade-offs during inference. Building on this, we introduce the Unified Autoregressive Reward Model (UniARM), a novel framework for multi-objective test-time alignment. UniARM jointly models all preference dimensions in a single parameter space, eliminating the need for independent parameters for each preference objective. es on larger-scale LLMs, enhancing its practical usability.

Related papers

• Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models [63.70401095689976]
  Vision-Language Models (VLMs) have broad potential in privacy-sensitive domains such as healthcare and finance.<n>We propose MoR, a federated alignment framework that combines GRPO with Mixture-of-Rewards for heterogeneousVLMs.<n>MoR consistently outperforms federated alignment baselines in generalization and cross-client adaptability.
  arXiv  Detail & Related papers  (2026-05-05T07:02:50Z)
• PCHC: Enabling Preference Conditioned Humanoid Control via Multi-Objective Reinforcement Learning [50.63196995993855]
  We propose a novel framework leveraging Multi-Objective Reinforcement Learning (MORL) to achieve Preference-Conditioned Humanoid Control (PCHC)<n>Our framework enables a single, preference-conditioned policy to exhibit a wide spectrum of diverse behaviors.
  arXiv  Detail & Related papers  (2026-03-25T07:55:37Z)
• ARM: Role-Conditioned Neuron Transplantation for Training-Free Generalist LLM Agent Merging [51.409102048965394]
  Agent-Role Merging (ARM) is an activation-guided, role-conditioned neuron transplantation method for model merging in LLM agents.<n>ARM improves existing merging methods from static natural language tasks to multi-turn agent scenarios.
  arXiv  Detail & Related papers  (2026-01-12T08:31:53Z)
• MAVIS: Multi-Objective Alignment via Value-Guided Inference-Time Search [12.710362645521466]
  We introduce MAVIS -- Multi-Objective Alignment via Value-Guided Inference-Time Search.<n>It enables dynamic control over LLM behavior without modifying the base model's weights.<n>We show that MAVIS outperforms baselines that fine-tune per-objective models and combine them post hoc.
  arXiv  Detail & Related papers  (2025-08-19T00:26:07Z)
• Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models [48.15777554876988]
  Traditional alignment methods often require retraining large pretrained models.<n>We propose a novel textitResidual Alignment Model (textitRAM) that formalizes the alignment process as a type of importance sampling.<n>We develop a resampling algorithm with iterative token-level decoding to address the common first-token latency issue in comparable methods.
  arXiv  Detail & Related papers  (2025-05-26T08:53:02Z)
• PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model [19.953213366157527]
  We propose Preference-aware ARM (PARM), a single unified ARM trained across all preference dimensions.<n>Experiments demonstrate that PARM reduces inference costs and achieves better alignment with preference vectors compared with existing methods.
  arXiv  Detail & Related papers  (2025-05-06T15:42:31Z)
• UC-MOA: Utility-Conditioned Multi-Objective Alignment for Distributional Pareto-Optimality [52.49062565901046]
  Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone for aligning large language models with human values.<n>Existing approaches struggle to capture the multi-dimensional, distributional nuances of human preferences.<n>We introduce Utility-Conditioned Multi-Objective Alignment (UC-MOA), a novel framework that overcomes these limitations.
  arXiv  Detail & Related papers  (2025-03-10T09:52:42Z)
• Robust Multi-Objective Preference Alignment with Online DPO [6.434799451791957]
  Multi-objective preference alignment is critical for developing AI systems that are personalizable, helpful, and safe.<n>Existing approaches are either computationally expensive to train or do not sufficiently steer model behaviors.<n>This paper introduces the Multi-Objective Online DPO algorithm, designed to robustly and efficiently align model behaviors with multiple, potentially conflicting human preferences.
  arXiv  Detail & Related papers  (2025-03-01T02:01:49Z)
• Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment [74.25832963097658]
  Multi-Objective Alignment (MOA) aims to align responses with multiple human preference objectives.<n>We find that DPO-based MOA approaches suffer from widespread preference conflicts in the data.
  arXiv  Detail & Related papers  (2025-02-20T08:27:00Z)
• 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)
• Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization [76.09576643028362]
  We present Multi-Objective Direct Preference Optimization (MODPO) for multiple alignment objectives. MODPO folds language modeling directly into reward modeling, training language models as implicit collective reward models. It theoretically yields the same optimal solutions as MORLHF but is practically more stable and efficient.
  arXiv  Detail & Related papers  (2023-10-05T17:35:26Z)
• PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm [0.18416014644193063]
  We propose a novel MORL algorithm that trains a single universal network to cover the entire preference space scalable to continuous robotic tasks. PD-MORL achieves up to 25% larger hypervolume for challenging continuous control tasks and uses an order of magnitude fewer trainable parameters compared to prior approaches.
  arXiv  Detail & Related papers  (2022-08-16T19:23:02Z)

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.