Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation
- URL: http://arxiv.org/abs/2404.01030v3
- Date: Wed, 1 May 2024 23:58:22 GMT
- Title: Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation
- Authors: Yixin Wan, Arjun Subramonian, Anaelia Ovalle, Zongyu Lin, Ashima Suvarna, Christina Chance, Hritik Bansal, Rebecca Pattichis, Kai-Wei Chang,
- Abstract summary: Even simple prompts could cause T2I models to exhibit conspicuous social bias in generated images.
We present the first extensive survey on bias in T2I generative models.
We discuss how these works define, evaluate, and mitigate different aspects of bias.
- Score: 47.770531682802314
- License: http://creativecommons.org/publicdomain/zero/1.0/
- Abstract: The recent advancement of large and powerful models with Text-to-Image (T2I) generation abilities -- such as OpenAI's DALLE-3 and Google's Gemini -- enables users to generate high-quality images from textual prompts. However, it has become increasingly evident that even simple prompts could cause T2I models to exhibit conspicuous social bias in generated images. Such bias might lead to both allocational and representational harms in society, further marginalizing minority groups. Noting this problem, a large body of recent works has been dedicated to investigating different dimensions of bias in T2I systems. However, an extensive review of these studies is lacking, hindering a systematic understanding of current progress and research gaps. We present the first extensive survey on bias in T2I generative models. In this survey, we review prior studies on dimensions of bias: Gender, Skintone, and Geo-Culture. Specifically, we discuss how these works define, evaluate, and mitigate different aspects of bias. We found that: (1) while gender and skintone biases are widely studied, geo-cultural bias remains under-explored; (2) most works on gender and skintone bias investigated occupational association, while other aspects are less frequently studied; (3) almost all gender bias works overlook non-binary identities in their studies; (4) evaluation datasets and metrics are scattered, with no unified framework for measuring biases; and (5) current mitigation methods fail to resolve biases comprehensively. Based on current limitations, we point out future research directions that contribute to human-centric definitions, evaluations, and mitigation of biases. We hope to highlight the importance of studying biases in T2I systems, as well as encourage future efforts to holistically understand and tackle biases, building fair and trustworthy T2I technologies for everyone.
Related papers
- A Critical Review of Predominant Bias in Neural Networks [19.555188118439883]
We find that there exists a persistent, extensive but under-explored confusion regarding these two types of biases.
We aim to restore clarity by providing two mathematical definitions for these two predominant biases and leveraging these definitions to unify a comprehensive list of papers.
arXiv Detail & Related papers (2025-02-16T07:55:19Z) - Fact-or-Fair: A Checklist for Behavioral Testing of AI Models on Fairness-Related Queries [85.909363478929]
In this study, we focus on 19 real-world statistics collected from authoritative sources.
We develop a checklist comprising objective and subjective queries to analyze behavior of large language models.
We propose metrics to assess factuality and fairness, and formally prove the inherent trade-off between these two aspects.
arXiv Detail & Related papers (2025-02-09T10:54:11Z) - Do Existing Testing Tools Really Uncover Gender Bias in Text-to-Image Models? [11.101062595569854]
Previous studies have shown that Text-to-Image (T2I) models can perpetuate or even amplify gender stereotypes when provided with neutral text prompts.
No existing work comprehensively compares the various detectors and understands how the gender bias detected by them deviates from the actual situation.
This study addresses this gap by validating previous gender bias detectors using a manually labeled dataset and comparing how the bias identified by various detectors deviates from the actual bias in T2I models.
arXiv Detail & Related papers (2025-01-27T04:47:19Z) - How far can bias go? -- Tracing bias from pretraining data to alignment [54.51310112013655]
This study examines the correlation between gender-occupation bias in pre-training data and their manifestation in LLMs.
Our findings reveal that biases present in pre-training data are amplified in model outputs.
arXiv Detail & Related papers (2024-11-28T16:20:25Z) - BIGbench: A Unified Benchmark for Social Bias in Text-to-Image Generative Models Based on Multi-modal LLM [8.24274551090375]
We introduce BIGbench, a unified benchmark for Biases of Image Generation.
Unlike existing benchmarks, BIGbench classifies and evaluates biases across four dimensions.
Our study also reveal new research directions about biases, such as the effect of distillation and irrelevant protected attributes.
arXiv Detail & Related papers (2024-07-21T18:09:40Z) - FAIntbench: A Holistic and Precise Benchmark for Bias Evaluation in Text-to-Image Models [7.30796695035169]
FAIntbench is a holistic and precise benchmark for biases in Text-to-Image (T2I) models.
We applied FAIntbench to evaluate seven recent large-scale T2I models and conducted human evaluation.
Results demonstrated the effectiveness of FAIntbench in identifying various biases.
arXiv Detail & Related papers (2024-05-28T04:18:00Z) - The Male CEO and the Female Assistant: Evaluation and Mitigation of Gender Biases in Text-To-Image Generation of Dual Subjects [58.27353205269664]
We propose the Paired Stereotype Test (PST) framework, which queries T2I models to depict two individuals assigned with male-stereotyped and female-stereotyped social identities.
PST queries T2I models to depict two individuals assigned with male-stereotyped and female-stereotyped social identities.
Using PST, we evaluate two aspects of gender biases -- the well-known bias in gendered occupation and a novel aspect: bias in organizational power.
arXiv Detail & Related papers (2024-02-16T21:32:27Z) - Quantifying Bias in Text-to-Image Generative Models [49.60774626839712]
Bias in text-to-image (T2I) models can propagate unfair social representations and may be used to aggressively market ideas or push controversial agendas.
Existing T2I model bias evaluation methods only focus on social biases.
We propose an evaluation methodology to quantify general biases in T2I generative models, without any preconceived notions.
arXiv Detail & Related papers (2023-12-20T14:26:54Z) - Towards Understanding Gender-Seniority Compound Bias in Natural Language
Generation [64.65911758042914]
We investigate how seniority impacts the degree of gender bias exhibited in pretrained neural generation models.
Our results show that GPT-2 amplifies bias by considering women as junior and men as senior more often than the ground truth in both domains.
These results suggest that NLP applications built using GPT-2 may harm women in professional capacities.
arXiv Detail & Related papers (2022-05-19T20:05:02Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.