# Efficient Fairness Auditing Across Guidance Scales in Text-to-Image Diffusion Models via Causal Abstraction

arXiv: https://arxiv.org/abs/2609.09486 · HTML: https://mlsanity.com/paper/2609.09486/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 25 of its 27 references that are in the map.
- First posted on arXiv 8 Sep 2026.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Causal Abstractions of Neural Networks](https://mlsanity.com/paper/2106.02997/) (2021)
- [Unified Concept Editing in Diffusion Models](https://mlsanity.com/paper/2308.14761/) (2023)
- [Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditing](https://mlsanity.com/paper/2001.00973/) (2020)
- [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022)
- [DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models](https://mlsanity.com/paper/2202.04053/) (2022)
- [Stable Bias: Analyzing Societal Representations in Diffusion Models](https://mlsanity.com/paper/2303.11408/) (2023)
- [Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations](https://mlsanity.com/paper/2303.02536/) (2023)
- [Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability](https://mlsanity.com/paper/2301.04709/) (2023)
- [Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness](https://mlsanity.com/paper/2302.10893/) (2023)
- [Editing Implicit Assumptions in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.08084/) (2023)
- [Abstracting Causal Models](https://mlsanity.com/paper/1812.03789/) (2018)
- [Finetuning Text-to-Image Diffusion Models for Fairness](https://mlsanity.com/paper/2311.07604/) (2023)
- [The Bias Amplification Paradox in Text-to-Image Generation](https://mlsanity.com/paper/2308.00755/) (2023)
- [Balancing Act: Distribution-Guided Debiasing in Diffusion Models](https://mlsanity.com/paper/2402.18206/) (2024)
- [T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image Generation](https://mlsanity.com/paper/2306.00905/) (2023)
- [Stable Diffusion Exposed: Gender Bias from Prompt to Image](https://mlsanity.com/paper/2312.03027/) (2023)
- [Neural Causal Abstractions](https://mlsanity.com/paper/2401.02602/) (2024)
- [A Framework for Assurance Audits of Algorithmic Systems](https://mlsanity.com/paper/2401.14908/) (2024)
- [BiasMap: Leveraging Cross-Attentions to Discover and Mitigate Hidden Social Biases in Text-to-Image Generation](https://mlsanity.com/paper/2509.13496/) (2025)
- [Causal Abstraction Inference under Lossy Representations](https://mlsanity.com/paper/2509.21607/) (2025)
- [Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scales](https://mlsanity.com/paper/2605.28036/) (2026)

## Abstract (arXiv)

Fairness auditing of text-to-image diffusion models often requires generating large numbers of images across sampling configurations, making comprehensive evaluation computationally expensive. We propose a causal-abstraction-based audit instrument for efficiently evaluating fairness under interventions on the classifier-free guidance scale. Given a fixed prompt and a target feature function, we represent the diffusion process as a low-level structural causal model and construct a corresponding high-level model over abstract denoising states. We characterize the projected causal structure, establish identifiability of the fairness-relevant interventional query, and provide sufficient conditions under which the high-level model preserves this query. A probabilistic transformer implements the high-level model as an amortized predictor of target-feature distributions across guidance scales. Experiments evaluate distributional fidelity, fairness-query accuracy, and computational efficiency. We present two auditing demonstrations: one using standard Stable Diffusion 1.5 and another using StayFair, a fairness-enhanced Stable Diffusion model, to examine their behavior across guidance scales.