๐ฎ
๐ฎ
The Ethereal
Procedural Fairness Failures in RLHF from Preference Averaging
August 10, 2026 ยท Grace Period ยท ๐ the ICLR 2026 Workshop on Algorithmic Fairness Across Alignment Procedures and Agentic Systems
Authors
M P V S Gopinadh, Karthik Kamuju, Kummari Avinash, John Joshua, Srinivasa Raju Rudraraju
arXiv ID
2608.10126
Category
cs.LG: Machine Learning
Cross-listed
cs.AI,
cs.CL
Citations
0
Venue
the ICLR 2026 Workshop on Algorithmic Fairness Across Alignment Procedures and Agentic Systems
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.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Machine Learning
๐ฎ
๐ฎ
The Ethereal
Continuous control with deep reinforcement learning
๐
๐
Old Age
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
๐
๐
Old Age
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
๐
๐
Old Age
SGDR: Stochastic Gradient Descent with Warm Restarts
๐ฎ
๐ฎ
The Ethereal