One Example Is Enough to Pass Fairness Benchmarks: Rethinking Fairness Evaluation for Aligned LLMs

arXiv:2609.14860v1 Announce Type: cross Abstract: Warning: This submission studies stereotypes and biases, and contains toxic and offensive examples, used for illustration purposes only. Fairness benchmarks such as BBQ have become the de facto standard for fairness evaluation across major model families. We argue that these benchmarks are too easy to support their role: training Qwen 2.5 7B Base with Group Relative Policy Optimization (GRPO) on a single BBQ example, or placing that example in context as a one-shot demonstration for in-context learning (ICL), lifts mean BBQ accuracy from 79.9% to 92.9% and 99.0%, respectively, closing 80% of the gap to its large-scale RLHF counterpart (96.1%) with GRPO, and surpassing it with ICL. These effects generalize across model families. A cross-conditioning analysis shows the improvement is carried by the reasoning traces generated by the model, and one example suffices to elicit a category-agnostic ``missing evidence'' reasoning pattern. We argue that BBQ-style multiple-choice abstention benchmarks measure a single structural cue, and a model that solves them does not thereby become fair. We call for evaluation suites that cover a broader spectrum of fairness alignment.

Related

• SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models
• A Multi-Domain Red Teaming Framework for Safety, Robustness, and Fairness Evaluation of Medical Large Language Models
• Adaptive Testing for LLM Evaluation: A Psychometric Alternative to Static Benchmarks

Source: arXiv cs.AI | 2026-09-15