Pith. sign in

REVIEW 12 cited by

Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2302.10893 v3 pith:47FQURYN submitted 2023-02-07 cs.LG cs.AIcs.CVcs.CYcs.HC

Felix Friedrich , Manuel Brack , Lukas Struppek , Dominik Hintersdorf , Patrick Schramowski , Sasha Luccioni , Kristian Kersting This is my paper
classification cs.LGcs.AIcs.CVcs.CYcs.HC
keywords modelsgenerativetheybiasesdemonstratediffusionfairfairness
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Generative AI models have recently achieved astonishing results in quality and are consequently employed in a fast-growing number of applications. However, since they are highly data-driven, relying on billion-sized datasets randomly scraped from the internet, they also suffer from degenerated and biased human behavior, as we demonstrate. In fact, they may even reinforce such biases. To not only uncover but also combat these undesired effects, we present a novel strategy, called Fair Diffusion, to attenuate biases after the deployment of generative text-to-image models. Specifically, we demonstrate shifting a bias, based on human instructions, in any direction yielding arbitrarily new proportions for, e.g., identity groups. As our empirical evaluation demonstrates, this introduced control enables instructing generative image models on fairness, with no data filtering and additional training required.

Discussion (0). Sign in to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Efficient bias mitigation in T2I diffusion models using Concept Graphs

    cs.AI 2026-07 conditional novelty 7.0 of 10

    Joint concept-graph alignment of Stable Diffusion’s text encoder and denoiser cuts fairness discrepancy ~30%, incoherent outputs 88%, and improves adversarial unlearning robustness.

  2. FairFlow: Demystifying and Mitigating Stereotype Bias in Text-to-Image Diffusion Transformers

    cs.CV 2026-07 conditional novelty 7.0 of 10

    Bias in MM-DiTs is mediated by sparse stage-wise semantic binding hubs, and sparse inference-time steering at those hubs mitigates gender, race, and intersectional stereotypes with low overhead.

  3. COVAriance-Induced Fairness Gap Penalty for Subgroup-Fair Clustering

    stat.ML 2026-07 conditional novelty 6.0 of 10

    A covariance quantity is proven exactly equal to a subgroup-fairness gap for clustering, yielding COVA-FC, a scalable algorithm that can also enforce marginal fairness.

  4. Calibrating Generative Models to Distributional Constraints

    stat.ML 2025-10 conditional novelty 6.0 of 10

    CGM-relax and CGM-reward fine-tune generative models to meet distributional constraints by minimizing a miscalibration penalty or a KL divergence to an estimated maximum-entropy tilt.

  5. Discovering Divergent Representations between Text-to-Image Models

    cs.CV 2025-09 conditional novelty 6.0 of 10

    An evolutionary algorithm discovers visual attributes that appear in one text-to-image model's outputs but not another's, and identifies the prompt concepts that trigger them.

  6. Understanding and evaluating computer vision models through the lens of counterfactuals

    cs.CV 2025-08 conditional novelty 6.0 of 10

    Counterfactual-based methods for concept attribution in classifiers and for dynamic bias evaluation and mitigation in text-to-image models.

  7. FAROS: Fair Graph Generation via Attribute Switching Mechanisms

    cs.LG 2025-07 conditional novelty 6.0 of 10

    FAROS switches sensitive attributes on an optimal fraction of nodes at an optimal diffusion step to produce fairer generated graphs with little accuracy loss.

  8. Multi-Group Proportional Representation for Text-to-Image Models

    cs.CV 2025-05 conditional novelty 6.0 of 10

    The authors apply the MPR metric (an integral probability metric) to text-to-image generation, derive tractable forms for linear and decision-tree function classes, and use it as a fine-tuning objective that reduces i...

  9. Mitigate One, Skew Another? Tackling Intersectional Biases in Text-to-Image Models

    cs.CV 2025-05 conditional novelty 6.0 of 10

    BiasConnect predicts how mitigating bias on one axis shifts bias on another axis in text-to-image models, and InterMit uses that to guide efficient multi-axis bias mitigation.

  10. Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation

    cs.LG 2026-07 conditional novelty 5.0 of 10

    A per-category best-of-K RL reward, multi-axis max@K, shifts SD3.5-M perceived-appearance distributions toward uniform coverage (Fairness Score +0.23 to +0.36) without quality loss.

  11. BioPro: Towards Difference-Aware Gender Fairness for Vision-Language Models

    cs.AI 2025-11 conditional novelty 5.0 of 10

    BioPro uses orthogonal projection on a gender-variation subspace to selectively debias vision-language models, reducing gender bias in neutral contexts while preserving explicit gender cues.

  12. FairJudge: Abstention-Aware Multimodal Judges for Fairness and Alignment Evaluation in Text-to-Image Models

    cs.CV 2025-10 conditional novelty 5.0 of 10

    An abstention-aware, label-constrained MLLM protocol plus two synthetic benchmarks improves social-attribute and alignment evaluation of text-to-image models on most tested attributes over CLIP/DeepFace.

Pith tools