AI ethics evidence index Search
Source-linked daily record
Evidence record 18681 · automatically gathered

Procedural Fairness Failures in RLHF from Preference Averaging

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 standar

Record details

Published: 10 August 2026
Source: arXiv fairness query
Category: Research
Topics: Bias & fairness · Safety & alignment
Retrieved: 12 August 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Agentic Harnesses: LLM-Driven Verification Layers for Robot Autonomy

arXiv · 10 August 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Neuro-symbolic pedagogical alignment (NSPA) for long-horizon classroom discourse analysis: Mitigating dialect bias via counterfactual preference optimization

Computers and Education: Artificial Intelligence · 12 August 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Bias Analysis of L2 Speaking Assessment Systems Using Concept Activation Vectors

arXiv · 6 August 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists

arXiv cs.AI · 5 August 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Inference-Time Policy Alignment for Fair Reinforcement Learning

arXiv fairness query · 31 July 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups

arXiv cs.CY · 31 July 2026

How to cite this record

ethics.ai (10 August 2026), “Procedural Fairness Failures in RLHF from Preference Averaging,” evidence record 18681, https://ethics.ai/record/18681 (originally published by arXiv fairness query).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.