[Paper] It Takes One to Bias Them All: Breaking Bad with One-Shot GRPO

Published: (June 9, 2026 at 10:44 AM EDT)
1 min read
Source: arXiv

Source: arXiv - 2606.10931v1

Overview

Warning: This paper contains several toxic and offensive statements. Modern large language models (LLMs) are typically aligned through large-scale post-training to ensure fair and reliable behavior. In this work, we investigate how easily such guardrails can be broken by Group Relative Policy Optimization (GRPO). We show that one-shot GRPO training on a single biased example is sufficient to induce systematic bias, with stereotype-driven reasoning generalizing across attributes, categories, and benchmarks. We further find that models differ in their susceptibility based on the initial likelihood of producing biased outputs. Our results reveal a critical vulnerability in post-training: alignment can be overridden by a single example.

Key Contributions

This paper presents research in the following areas:

  • cs.CL

Methodology

Please refer to the full paper for detailed methodology.

Practical Implications

This research contributes to the advancement of cs.CL.

Authors

  • Naihao Deng
  • Yilun Zhu
  • Naichen Shi
  • Clayton Scott
  • Rada Mihalcea

Paper Information

  • arXiv ID: 2606.10931v1
  • Categories: cs.CL
  • Published: June 9, 2026
  • PDF: Download PDF
0 views
Back to Blog

Related posts

Read more »