Bayesian Preference Learning for Test-Time Steerable Reward Models

• URL: http://arxiv.org/abs/2602.08819v1
• Date: Mon, 09 Feb 2026 15:55:56 GMT
• Title: Bayesian Preference Learning for Test-Time Steerable Reward Models
• Authors: Jiwoo Hong, Shao Tang, Zhipeng Wang,
• Abstract summary: We propose Variational In-Context Reward Modeling, which enables test-time steerability via in-context preference demonstrations.<n>We show that I CRM gains 34% accuracy on SafeRLHF and 9% accuracy on RM-Bench in the single-objective setting.<n>We further study the practical applicability of I CRM for RL training, showing that it can effectively encode verifiable rewards by outperforming a conventional RM in math reasoning.
• Score: 9.817455218872645
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reward models are central to aligning language models with human preferences via reinforcement learning (RL). As RL is increasingly applied to settings such as verifiable rewards and multi-objective alignment, RMs are expected to encode more complex and multifaceted preference distributions. However, classifier RMs remain static once trained, limiting their adaptability at test time. We propose Variational In-Context Reward Modeling (ICRM), a novel Bayesian reward modeling objective that enables test-time steerability via in-context preference demonstrations. ICRM casts reward modeling as amortized variational inference over a latent preference probability under the Bradley-Terry model using a conjugate Beta prior. We show that ICRM adapt to unseen preference distributions at test time for both single and multi-objective settings. With more in-context demonstrations, ICRM gains 34% accuracy on SafeRLHF and 9% accuracy on RM-Bench in the single-objective setting, while widening the Pareto frontier with a 4% gain in hypervolume on helpfulness and refusal benchmarks. We further study the practical applicability of ICRM for RL training, showing that it can effectively encode verifiable rewards by outperforming a conventional RM in math reasoning. Finally, we provide theoretical guarantees that the variational objective admits a global interior optimum with finite confidence, and we analyze how KL regularization mitigates reward over-optimization.

Related papers

• Learning Ordinal Probabilistic Reward from Preferences [25.069054134899744]
  We introduce a novel reward modeling paradigm: Probabilistic Reward Model (PRM)<n>Instead of modeling reward as a deterministic scalar, our approach treats it as a random variable, learning a full probability distribution for the quality of each response.<n>Building on OPRM, we propose a data-efficient training strategy called Region Flooding Tuning (RgFT)
  arXiv  Detail & Related papers  (2026-02-13T06:43:02Z)
• Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling [49.41422138354821]
  We propose a principled reward modeling framework that integrates non-negative factor analysis into the Bradley-Terry preference model.<n>BNRM represents rewards through a sparse, non-negative latent factor generative process.<n>We show that BNRM substantially mitigates reward over-optimization, improves robustness under distribution shifts, and yields more interpretable reward decompositions than strong baselines.
  arXiv  Detail & Related papers  (2026-02-11T08:14:11Z)
• Multi-Agent Collaborative Reward Design for Enhancing Reasoning in Reinforcement Learning [13.30869366778628]
  CRM is a framework that replaces a single black-box reward model with a coordinated team of specialist evaluators.<n>To support training and assessment, we introduce rewardBench, a benchmark and training suite aligned with the collaborative structure of CRM.
  arXiv  Detail & Related papers  (2025-11-20T10:12:34Z)
• One Model to Critique Them All: Rewarding Agentic Tool-Use via Efficient Reasoning [54.580646706013965]
  Reward models (RMs) play a critical role in aligning large language models with human preferences.<n>We introduce ToolRM, a family of lightweight generative RMs tailored for general tool-use scenarios.<n>To build these models, we propose a novel pipeline that constructs pairwise preference data using rule-based scoring and multidimensional sampling.
  arXiv  Detail & Related papers  (2025-10-30T06:08:27Z)
• Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking [78.69179041551014]
  We propose an information-theoretic reward modeling framework based on the Information Bottleneck principle.<n>We show that InfoRM filters out preference-irrelevant information to alleviate reward misgeneralization.<n>We also introduce IBL, a distribution-level regularization that penalizes such deviations, effectively expanding the optimization landscape.
  arXiv  Detail & Related papers  (2025-10-15T15:51:59Z)
• APLOT: Robust Reward Modeling via Adaptive Preference Learning with Optimal Transport [37.21695864040979]
  The reward model (RM) plays a crucial role in aligning Large Language Models (LLMs) with human preferences through Reinforcement Learning.<n>This paper introduces an effective enhancement to BT-based RMs through an adaptive margin mechanism.
  arXiv  Detail & Related papers  (2025-10-13T03:13:28Z)
• Beyond Monolithic Rewards: A Hybrid and Multi-Aspect Reward Optimization for MLLM Alignment [1.8552770604791606]
  We propose a hybrid reward modeling framework that integrates complementary reward paradigms.<n>We show consistent improvements across different multimodal benchmarks when applying hybrid and multi-aspect reward modeling.<n>Our best performing model in the 3B family achieves an overall average improvement of 9.5% across general and math reasoning tasks.
  arXiv  Detail & Related papers  (2025-10-06T18:53:23Z)
• Activation Reward Models for Few-Shot Model Alignment [77.37511364793515]
  We introduce Activation Reward Models (Activation RMs)<n>Activation RMs leverage activation steering to construct well-aligned reward signals using minimal supervision and no additional model finetuning.<n>We demonstrate the effectiveness of Activation RMs in mitigating reward hacking behaviors, highlighting their utility for safety-critical applications.
  arXiv  Detail & Related papers  (2025-07-02T05:10:29Z)
• Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment [35.80989342492335]
  noisy preferences in human feedback can lead to reward misgeneralization.<n>This paper aims to identify how noisy preferences differ from human-aligned preferences in reward modeling.<n>We propose an online Collaborative Reward Modeling framework to achieve robust preference learning.
  arXiv  Detail & Related papers  (2025-05-15T10:58:20Z)
• RM-R1: Reward Modeling as Reasoning [81.50471199906738]
  Reasoning Reward Models (ReasRMs) formulate reward modeling as a reasoning task.<n>We propose a reasoning-oriented training pipeline and train a family of ReasRMs, RM-R1.<n>Our models achieve state-of-the-art performance across three reward model benchmarks on average.
  arXiv  Detail & Related papers  (2025-05-05T06:11:12Z)
• RewardBench: Evaluating Reward Models for Language Modeling [100.28366840977966]
  We present RewardBench, a benchmark dataset and code-base for evaluation of reward models. The dataset is a collection of prompt-chosen-rejected trios spanning chat, reasoning, and safety. On the RewardBench leaderboard, we evaluate reward models trained with a variety of methods.
  arXiv  Detail & Related papers  (2024-03-20T17:49:54Z)
• WARM: On the Benefits of Weight Averaged Reward Models [63.08179139233774]
  We propose Weight Averaged Reward Models (WARM) to mitigate reward hacking. Experiments on summarization tasks, using best-of-N and RL methods, shows that WARM improves the overall quality and alignment of LLM predictions.
  arXiv  Detail & Related papers  (2024-01-22T18:27:08Z)
• On Diversified Preferences of Large Language Model Alignment [51.26149027399505]
  This paper presents the first quantitative analysis of the experimental scaling law for reward models with varying sizes. Our analysis reveals that the impact of diversified human preferences depends on both model size and data size. Larger models with sufficient capacity mitigate the negative effects of diverse preferences, while smaller models struggle to accommodate them.
  arXiv  Detail & Related papers  (2023-12-12T16:17:15Z)

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.