# Statistical attribute alignment for black-box generative AI via output post-processing

arXiv: https://arxiv.org/abs/2609.31607 · HTML: https://mlsanity.com/paper/2609.31607/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 122 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Builds on (most cited first, 20 of 20)

- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [AI Alignment: A Comprehensive Survey](https://mlsanity.com/paper/2310.19852/) (2023)
- [Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness](https://mlsanity.com/paper/2302.10893/) (2023)
- [Machine Learning for Synthetic Data Generation: A Review](https://mlsanity.com/paper/2302.04062/) (2023)
- [A Distributional Approach to Controlled Text Generation](https://mlsanity.com/paper/2012.11635/) (2020)
- [Finetuning Text-to-Image Diffusion Models for Fairness](https://mlsanity.com/paper/2311.07604/) (2023)
- [Artificial Intelligence Index Report 2025](https://mlsanity.com/paper/2504.07139/) (2025)
- [Automatic Interactive Evaluation for Large Language Models with State Aware Patient Simulator](https://mlsanity.com/paper/2403.08495/) (2024)
- [Augmenting medical image classifiers with synthetic data from latent diffusion models](https://mlsanity.com/paper/2308.12453/) (2023)
- [Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making](https://mlsanity.com/paper/2312.04772/) (2023)
- [AI Agents for Conversational Patient Triage: Preliminary Simulation-Based Evaluation with Real-World EHR Data](https://mlsanity.com/paper/2506.04032/) (2025)
- [General Synthetic-Powered Inference](https://mlsanity.com/paper/2509.20345/) (2025)
- [Can Vision-Language Models Replace Human Annotators: A Case Study with CelebA Dataset](https://mlsanity.com/paper/2410.09416/) (2024)
- [Can Prompt Modifiers Control Bias? A Comparative Analysis of Text-to-Image Generative Models](https://mlsanity.com/paper/2406.05602/) (2024)
- [DiffusionWorldViewer: Exposing and Broadening the Worldview Reflected by Generative Text-to-Image Models](https://mlsanity.com/paper/2309.09944/) (2023)
- [Harnessing Synthetic Data from Generative AI for Statistical Inference](https://mlsanity.com/paper/2603.05396/) (2026)

## Abstract (arXiv)

Generative AI systems are increasingly used, but aligning their outputs with user requirements poses a continuing challenge. Here, we aim to ensure that the distribution of an attribute of an AI-generated output aligns with a user-specified target. This is motivated by examples such as fairness, where we want to ensure that a protected attribute (e.g., gender, race, or age categories) follows a desired distribution, and synthetic data generation, where we want the generated data to be representative of a target distribution. We study the practically important black-box access setting, where a user can repeatedly query a generative AI model. The goal is to return m≥ 1 outputs whose joint attribute distribution is as close as possible to this target. For both exact and approximate alignment, we develop algorithms that minimize the expected number of queries to the generator, and we further demonstrate their optimality as the number of requested outputs m rightarrow ∞. Experiments on text-to-image generation and geocoded persona generation tasks show that our post-processing algorithms improve statistical attribute alignment, complementing prompting-based interventions.