Procedural Fairness Failures in RLHF from Preference Averaging

• URL: http://arxiv.org/abs/2608.10126v1
• Date: Mon, 10 Aug 2026 18:38:16 GMT
• Title: Procedural Fairness Failures in RLHF from Preference Averaging
• Abstract summary: This work defines procedural fairness in alignment and shows that standard RLHF violates this via preference averaging.<n> Preference-Aware RLHF (PA-RLHF) is introduced, separating optimization across preference modes at the reward learning stage.<n>In a controlled setting, PA-RLHF improves overall alignment accuracy from 46.9% to 67.9% and reduces the fairness gap between best and worst aligned groups from 15.9 to 9.6 percentage points.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement Learning from Human Feedback (RLHF) aggregates heterogeneous preferences into a single reward model, assuming preference homogeneity. When preferences are heterogeneous, this aggregation induces a procedural fairness failure where majority preference groups dominate reward learning while minority preferences are systematically under-represented. This work defines procedural fairness in alignment as preserving distinct preference signals during reward modeling and shows that standard RLHF violates this via preference averaging. Preference-Aware RLHF (PA-RLHF) is introduced, separating optimization across preference modes at the reward learning stage. In a controlled setting, PA-RLHF improves overall alignment accuracy from 46.9% to 67.9% and reduces the fairness gap between best and worst aligned groups from 15.9 to 9.6 percentage points. These results show that procedural fairness failures in alignment can arise from structural design choices in reward learning, even in controlled, noise-free settings, with direct implications for large language models and agentic systems, where biased reward models can compound inequities across sequential decisions.

Related papers

• Unbiased Alignment for Large Language Models with Noisy Preferences [74.69408994904965]
  We present a theoretical framework for unbiased alignment, introducing the Unbiased Reward Model (URM) loss and the Unbiased Direct Preference Optimization (UDPO) loss.<n>By mathematically correcting the distortion induced by preference noise, our novel objectives enable unbiased model training directly from noisy datasets.
  arXiv  Detail & Related papers  (2026-07-03T12:04:43Z)
• Personalized Group Relative Policy Optimization for Heterogenous Preference Alignment [13.085014101959118]
  We introduce Personalized GRPO, a novel alignment framework that decouples advantage estimation from batch statistics.<n>We evaluate P-GRPO across diverse tasks and find that it consistently achieves faster convergence and higher rewards than standard GRPO.
  arXiv  Detail & Related papers  (2026-02-17T19:00:43Z)
• Positive-Unlabeled Reinforcement Learning Distillation for On-Premise Small Models [130.8912476550625]
  We propose a positive-unlabeled (PU) reinforcement learning distillation method for on-premise small-model deployment.<n>Our method distills the teacher's preference-optimization capability from black-box generations into a locally trainable student.<n>Experiments demonstrate that our method achieves consistently strong performance under a low-cost setting.
  arXiv  Detail & Related papers  (2026-01-28T15:14:50Z)
• Reward-Augmented Data Enhances Direct Preference Alignment of LLMs [63.32585910975191]
  We introduce reward-conditioned Large Language Models (LLMs) that learn from the entire spectrum of response quality within the dataset.<n>We show that our approach consistently boosts DPO by a considerable margin.<n>Our method not only maximizes the utility of preference data but also mitigates the issue of unlearning, demonstrating its broad effectiveness beyond mere data expansion.
  arXiv  Detail & Related papers  (2024-10-10T16:01:51Z)
• On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization [39.29350451006295]
  preference matching (PM) RLHF is a novel approach that aligns large language models with the preference distribution of the reward model under the Bradley--Terry--Luce/Plackett--Luce model.<n>Central to our approach is a PM regularizer that takes the form of the negative logarithm of the LLM's policy probability distribution over responses.<n>Experiments show a 29% to 41% improvement in alignment with human preferences, as measured by a certain metric, compared to standard RLHF.
  arXiv  Detail & Related papers  (2024-05-26T07:00:05Z)
• RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation [24.374185140811115]
  Reinforcement learning from human feedback (RLHF) has been an effective technique for aligning AI systems with human values. In this paper, we focus on addressing the issues due to the inherent heterogeneity in human preferences, as well as their potential strategic behavior in providing feedback. We propose two frameworks to address heterogeneous human feedback in principled ways: personalization-based one and aggregation-based one.
  arXiv  Detail & Related papers  (2024-04-30T23:57:23Z)
• Provable Multi-Party Reinforcement Learning with Diverse Human Feedback [63.830731470186855]
  Reinforcement learning with human feedback (RLHF) is an emerging paradigm to align models with human preferences. We show how traditional RLHF approaches can fail since learning a single reward function cannot capture and balance the preferences of multiple individuals. We incorporate meta-learning to learn multiple preferences and adopt different social welfare functions to aggregate the preferences across multiple parties.
  arXiv  Detail & Related papers  (2024-03-08T03:05:11Z)
• MaxMin-RLHF: Alignment with Diverse Human Preferences [101.57443597426374]
  Reinforcement Learning from Human Feedback (RLHF) aligns language models to human preferences by employing a singular reward model derived from preference data.<n>We learn a mixture of preference distributions via an expectation-maximization algorithm to better represent diverse human preferences.<n>Our algorithm achieves an average improvement of more than 16% in win-rates over conventional RLHF algorithms.
  arXiv  Detail & Related papers  (2024-02-14T03:56:27Z)
• Direct Preference Optimization: Your Language Model is Secretly a Reward Model [119.65409513119963]
  We introduce a new parameterization of the reward model in RLHF that enables extraction of the corresponding optimal policy in closed form. The resulting algorithm, which we call Direct Preference Optimization (DPO), is stable, performant, and computationally lightweight. Our experiments show that DPO can fine-tune LMs to align with human preferences as well as or better than existing methods.
  arXiv  Detail & Related papers  (2023-05-29T17:57:46Z)

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.