Mitigate One, Skew Another? Tackling Intersectional Biases in Text-to-Image Models (2025.findings-emnlp)
Copied to clipboard
Pushkar Shukla, Aditya Chinchure, Emily Diana, Alexander Tolbert, Kartik Hosanagar, Vineeth N. Balasubramanian, Leonid Sigal, Matthew A. Turk
| Challenge: | a new tool for analyzing and quantifying bias interactions in text-to-image models is being developed . a bias in text models can be deeply interrelated, but measuring such effects quantitatively remains a challenge. |
| Approach: | They propose a tool to quantify bias interactions in text-to-image models by analyzing and quantifying bias interactions along bias axes. |
| Outcome: | a new tool analyzes and quantifies bias interactions in text-to-image models . estimates show strong correlations with observed post-mitigation outcomes . |
Similar Papers
The Male CEO and the Female Assistant: Evaluation and Mitigation of Gender Biases in Text-To-Image Generation of Dual Subjects (2025.acl-long)
Copied to clipboard
| Challenge: | Recent large-scale T2I models like DALLE-3 have made progress in reducing gender stereotypes when generating single-person images. |
| Approach: | They propose a framework that queries T2I models to depict two individuals with gender-stereotyped social identities to evaluate gender biases. |
| Outcome: | The proposed framework reduces gender stereotypes when generating images with more than one person. |
Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information (2024.naacl-short)
Copied to clipboard
| Challenge: | Existing approaches to mitigate social biases require explicit annotation of demographic information for each sample. |
| Approach: | They propose a method that leverages predefined demographic texts and incorporates a regularization term during the fine-tuning process to mitigate bias in language models. |
| Outcome: | The proposed method outperforms debiasing methods with limited demographic-annotated data. |
How Far Can It Go? On Intrinsic Gender Bias Mitigation for Text Classification (2023.eacl-main)
Copied to clipboard
| Challenge: | a growing interest in exploring how gender bias pertains in contextualized language models has been generated . intrinsic mitigation strategies and bias metrics have been proposed to mitigate gender bias in contextualised language models . |
| Approach: | They propose to use different intrinsic bias mitigation strategies to mitigate gender bias in contextualized language models. |
| Outcome: | The proposed probe shows that some mitigation techniques can hide gender bias . the probe also shows that not all mitigation techniques fool extrinsic bias despite their use . |
T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image Generation (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in text-to-image generative models have produced high quality images with a breakthrough of inference speed. |
| Approach: | They propose a text-to-image association test framework that quantifies implicit stereotypes between concepts and valence and those in images. |
| Outcome: | The proposed framework quantifies implicit stereotypes between concepts and valence and those in images. |
More than Minorities and Majorities: Understanding Multilateral Bias in Language Generation (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on bias dataset construction and mitigation focus on one demographic group . in real-world applications, there are more than two demographic groups at risk of the same bias. |
| Approach: | They propose to analyze and reduce biases across multiple demographic groups using a multi-demographic bias dataset. |
| Outcome: | The proposed method can mitigate biases among multiple demographic groups effectively, the authors show . |
Resampled Datasets Are Not Enough: Mitigating Societal Bias Beyond Single Attributes (2024.emnlp-main)
Copied to clipboard
Yusuke Hirota, Jerone Andrews, Dora Zhao, Orestis Papakyriakopoulos, Apostolos Modas, Yuta Nakashima, Alice Xiang
| Challenge: | Traditional approaches only target labeled attributes, ignoring biases from unlabeled ones. |
| Approach: | They propose a method that ensures protected group independence from all attributes and mitigates inpainting biases through data filtering. |
| Outcome: | The proposed approach achieves an average reduction of 46.1% in leakage-based bias metrics for multi-label classification and 74.8% for image captioning. |
A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning (2022.aacl-main)
Copied to clipboard
| Challenge: | Large-scale, pretrained vision-language models are growing in popularity due to impressive performance on downstream tasks with minimal finetuning. |
| Approach: | They propose to apply ranking metrics to image-text representations to investigate bias measures and debiasing methods to reduce various bias measures. |
| Outcome: | The proposed model reduces bias measures with minimal degradation to image-text representations. |
Benchmarking Intersectional Biases in NLP (2022.naacl-main)
Copied to clipboard
| Challenge: | Recent work on fairness of machine learning models has focused on how to debias, but research on the fairness and performance of biased/debiased models on downstream prediction tasks has been limited. |
| Approach: | They assess intersectional bias - fairness across multiple demographic dimensions . they highlight possible causes and make recommendations for future NLP debiasing research. |
| Outcome: | The proposed approaches fare well in terms of fairness-accuracy trade-off, but are unable to effectively alleviate bias in downstream tasks. |
Unpacking Bias: An Empirical Study of Bias Measurement Metrics, Mitigation Algorithms, and Their Interactions (2024.lrec-main)
Copied to clipboard
| Challenge: | Word embeddings (WE) models reflect gender, racial, and religious stereotypes from the corpus on which they are trained. |
| Approach: | They propose a method that carefully controls for word sets and vector normalization to address these factors. |
| Outcome: | The proposed method detects consistency between different mitigation methods and the evaluation words used by the mitigation methods. |
Misalignment Attack on Text-to-Image Models via Text Embedding Optimization and Inversion (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Text embedding is a key component of modern NLP models but also poses additional risks. |
| Approach: | They propose a framework that optimizes embeddings and inverts them to obtain misaligned prompts. |
| Outcome: | The proposed framework exploits the continuity and distribution characteristics of text embeddings to obtain misaligned prompts of discrete tokens. |