BiasMap: Leveraging Cross-Attentions to Discover and Mitigate Hidden Social Biases in Text-to-Image Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chakraborty, Rajatsubhra, Che, Xujun, Xu, Depeng, Faklaris, Cori, Niu, Xi, Yuan, Shuhan
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Mitigating Smishing: Challenges and Future Work
by: Faklaris, Cori
Published: (2024)

Digital Privacy for Migrants: Exploring Current Research Trends and Future Prospects
by: Tabassum, Sarah, et al.
Published: (2024)

Unlocking High-Fidelity Molecular Generation from Mass Spectra via Dual-Stream Line Graph Diffusion
by: Che, Xujun, et al.
Published: (2026)

Comparative Analysis of Formula and Structure Prediction from Tandem Mass Spectra
by: Che, Xujun, et al.
Published: (2026)

DM-QPMNET: Dual-modality fusion network for cell segmentation in quantitative phase microscopy
by: Chakraborty, Rajatsubhra, et al.
Published: (2025)

Discover and Mitigate Multiple Biased Subgroups in Image Classifiers
by: Zhang, Zeliang, et al.
Published: (2024)

SOBON: The Inner Yajna and Soma Generation in Vedic Tradition
by: Mukhopadhyay, Dr Rajatsubhra
Published: (2025)

Do We Need Large VLMs for Spotting Soccer Actions?
by: Chakraborty, Ritabrata, et al.
Published: (2025)

BadSAD: Clean-Label Backdoor Attacks against Deep Semi-Supervised Anomaly Detection
by: Cheng, He, et al.
Published: (2024)

MIST: Mitigating Intersectional Bias with Disentangled Cross-Attention Editing in Text-to-Image Diffusion Models
by: Yesiltepe, Hidir, et al.
Published: (2024)

BiasIG: Benchmarking Multi-dimensional Social Biases in Text-to-Image Models
by: Luo, Hanjun, et al.
Published: (2026)

Discovering and Mitigating Visual Biases through Keyword Explanation
by: Kim, Younghyun, et al.
Published: (2023)

TruthLens:A Training-Free Paradigm for DeepFake Detection
by: Chakraborty, Ritabrata, et al.
Published: (2025)

Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation
by: Wan, Yixin, et al.
Published: (2024)

Hidden Bias in the Machine: Stereotypes in Text-to-Image Models
by: Porikli, Sedat, et al.
Published: (2025)

Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search
by: Plitsis, Manos, et al.
Published: (2025)

Building Nucleosome Positioning Maps: Discovering Hidden Gems
by: Yosef Masoudi‐Sobhanzadeh, et al.
Published: (2025)

How Bias Binds: Measuring Hidden Associations for Bias Control in Text-to-Image Compositions
by: Li, Jeng-Lin, et al.
Published: (2025)

Mitigating Biases in Language Models via Bias Unlearning
by: Liu, Dianqing, et al.
Published: (2025)

BiasDora: Exploring Hidden Biased Associations in Vision-Language Models
by: Raj, Chahat, et al.
Published: (2024)

Aligned but Stereotypical? The Hidden Influence of System Prompts on Social Bias in LVLM-Based Text-to-Image Models
by: Park, NaHyeon, et al.
Published: (2025)

Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information
by: Iskander, Shadi, et al.
Published: (2024)

Cross-Modal Mapping: Mitigating the Modality Gap for Few-Shot Image Classification
by: Yang, Xi, et al.
Published: (2024)

LLaVA-MLB: Mitigating and Leveraging Attention Bias for Training-Free Video LLMs
by: Shen, Leqi, et al.
Published: (2025)

Breaking Bias, Building Bridges: Evaluation and Mitigation of Social Biases in LLMs via Contact Hypothesis
by: Raj, Chahat, et al.
Published: (2024)

The Male CEO and the Female Assistant: Evaluation and Mitigation of Gender Biases in Text-To-Image Generation of Dual Subjects
by: Wan, Yixin, et al.
Published: (2024)

Mitigate One, Skew Another? Tackling Intersectional Biases in Text-to-Image Models
by: Shukla, Pushkar, et al.
Published: (2025)

On Mitigating Affinity Bias through Bandits with Evolving Biased Feedback
by: Faw, Matthew, et al.
Published: (2025)

Exploring Unknown Social Networks for Discovering Hidden Nodes
by: Tsugawa, Sho, et al.
Published: (2025)

CountCluster: Training-Free Object Quantity Guidance with Cross-Attention Map Clustering for Text-to-Image Generation
by: Lee, Joohyeon, et al.
Published: (2025)

Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach
by: Shirafuji, Daiki, et al.
Published: (2024)

Evaluating and Mitigating Bias in AI-Based Medical Text Generation
by: Chen, Xiuying, et al.
Published: (2025)

Causal ATE Mitigates Unintended Bias in Controlled Text Generation
by: Madhavan, Rahul, et al.
Published: (2023)

Leveraging Depth Maps and Attention Mechanisms for Enhanced Image Inpainting
by: Park, Jin Hyun, et al.
Published: (2025)

FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models
by: Fu, Zihao, et al.
Published: (2025)

Rumor Mitigation in Social Media Platforms with Deep Reinforcement Learning
by: Su, Hongyuan, et al.
Published: (2024)

FairT2I: Mitigating Social Bias in Text-to-Image Generation via Large Language Model-Assisted Detection and Attribute Rebalancing
by: Sakurai, Jinya, et al.
Published: (2025)

Social Bias in LLM-Generated Code: Benchmark and Mitigation
by: Rabbi, Fazle, et al.
Published: (2026)

VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models
by: Huang, Jen-tse, et al.
Published: (2025)

PromptMap: Supporting Exploratory Text-to-Image Generation
by: Guo, Yuhan, et al.
Published: (2025)