Skip to content
Back to skills

Generative Classifiers Avoid Shortcut Solutions

ASecurity

**arXiv ID:** 2512.25034 **Authors:** Alexander C. Li, Ananya Kumar, Deepak Pathak **Published:** 2025-12-31T18:31:46Z **Abstract:** Discriminative approaches to classification often learn shortcuts that hold in-distribution but fail even under minor distribution shift. This failure mode stems from an overreliance on features that are spuriously correlated with the label. We show that generative classifiers, which use class-conditional generative models, can avoid this issue by modeling all f...

  • 3 stars
  • 0 votes
  • 0 copies
  • 5 views
  • Added September 11, 2026
toolsperformance

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill generative-classifiers-avoid-shortcut-solutions --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Generative Classifiers Avoid Shortcut Solutions?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Generative Classifiers Avoid Shortcut Solutions
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-generative-classifiers-avoid-shortcut-solutions/badge)](https://www.skillsdirectory.com/skills/hiyenwong-generative-classifiers-avoid-shortcut-solutions)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# Generative Classifiers Avoid Shortcut Solutions

**arXiv ID:** 2512.25034
**Authors:** Alexander C. Li, Ananya Kumar, Deepak Pathak
**Published:** 2025-12-31T18:31:46Z
**Abstract:**
Discriminative approaches to classification often learn shortcuts that hold in-distribution but fail even under minor distribution shift. This failure mode stems from an overreliance on features that are spuriously correlated with the label. We show that generative classifiers, which use class-conditional generative models, can avoid this issue by modeling all features, both core and spurious, instead of mainly spurious ones. These generative classifiers are simple to train, avoiding the need for specialized augmentations, strong regularization, extra hyperparameters, or knowledge of the specific spurious correlations to avoid. We find that diffusion-based and autoregressive generative classifiers achieve state-of-the-art performance on five standard image and text distribution shift benchmarks and reduce the impact of spurious correlations in realistic applications, such as medical or satellite datasets. Finally, we carefully analyze a Gaussian toy setting to understand the inductive biases of generative classifiers, as well as the data properties that determine when generative classifiers outperform discriminative ones.

## Skill Description

This skill is generated from the arXiv paper: Generative Classifiers Avoid Shortcut Solutions (2512.25034).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2512.25034](http://arxiv.org/abs/2512.25034v1)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in tools →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.