---
title: "Adversarial Prefixes"
description: "1 posts about Adversarial Prefixes, summarised, each linking to the original."
---

# Adversarial Prefixes
> 1 posts about Adversarial Prefixes, summarised, each linking to the original.

## Articles

### [FairStress: A deeper evaluation of fairness in LLM decision-making](https://yomu.fyi/post/fairstress-a-deeper-evaluation-of-fairness-in-llm-decision-making.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Kyle Wiggers
- Published: Oct 20, 2026
- Type: Benchmark

FairStress is a benchmark for measuring demographic fairness in LLMs beyond the final output decision, evaluating how readily models change choices when challenged by adversarial prefixes. It expands 300 two-candidate scenarios across 29 domains into over 13 million test cases by varying demographic identity and persuasive arguments. Across 15 models, the benchmark revealed anti-stereotypical over-correction: models abandoned correct decisions more readily when doing so favored a minority-coded candidate, with average symmetry gaps of 6.9 and 9.3 percentage points for implied and explicit identity. Most debiasing methods, including self-critique and activation steering, did not reliably reduce the asymmetry and sometimes harmed accuracy; one activation-steering method dropped Qwen2.5-7B-Instruct’s accuracy from 98% to 47%. Counterfactual chain-of-thought, which asks models to reconsider with swapped identities, reduced the asymmetry gap while largely preserving accuracy, though it did not remove all biases.