paper-with-me

Papers

Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)

2024-10-25 · Leander Girrbach, Stephan Alaniz, Yiran Huang, Trevor Darrell, Zeynep Akata

Pre-trained large language models (LLMs) have been reliably integrated with visual input for multimodal tasks. The widespread adoption of instruction-tuned image-to-text vision-language assistants (VLAs) like LLaVA and InternVL necessitates evaluating gender biases. We study gender bias in 22 popular open-source VLAs with respect to personality traits, skills, and occupations. Our results show that VLAs replicate human biases likely present in the data, such as real-world occupational imbalances. Similarly, they tend to attribute more skills and positive personality traits to women than to men, and we see a consistent tendency to associate negative personality traits with men. To eliminate the gender bias in these models, we find that fine-tuning-based debiasing methods achieve the best trade-off between debiasing and retaining performance on downstream tasks. We argue for pre-deploying gender bias assessment in VLAs and motivate further development of debiasing strategies to ensure equitable societal outcomes. Code is available at https://github.com/ExplainableML/vla-gender-bias.

📄 PDF Abstract BibTeX arXiv:2410.19314

Code (1)

explainableml/vla-gender-bias 공식 구현 pytorch

Tasks

AttributeImage to text

Similar Papers 제목 키워드 기반

Revealing Hidden Bias in AI: Lessons from Large Language Models

2024-10-22 · Django Beatty, Kritsada Masanthia, Teepakorn Kaphol, Niphan Sethi

As large language models (LLMs) become integral to recruitment processes, concerns about AI-induced bias have intensified. This study examines biases in candidate interview reports generated by Claude 3.5 Sonnet, GPT-4o,…

Fairness

Mitigation of Gender and Ethnicity Bias in AI-Generated Stories through Model Explanations

2025-09-03 · Martha O. Dimgba, Sharon Oba, Ameeta Agrawal, Philippe J. Giabbanelli arxiv

Language models have been shown to propagate social bias through their output, particularly in the representation of gender and ethnicity. This paper investigates gender and ethnicity biases in AI-generated occupational …

Prompt Engineering

DR.GAP: Mitigating Bias in Large Language Models using Gender-Aware Prompting with Demonstration and Reasoning

2025-02-17 · Hongye Qiu, Yue Xu, Meikang Qiu, Wenjie Wang

Large Language Models (LLMs) exhibit strong natural language processing capabilities but also inherit and amplify societal biases, including gender bias, raising fairness concerns. Existing debiasing methods face signifi…

coreference-resolutionCoreference ResolutionFairness

GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models

2024-06-20 · Tao Zhang, Ziqian Zeng, Yuxiang Xiao, Huiping Zhuang 외

Large Language Models (LLMs) are prone to generating content that exhibits gender biases, raising significant ethical concerns. Alignment, the process of fine-tuning LLMs to better align with desired behaviors, is recogn…

8k

Beyond Binary Gender Labels: Revealing Gender Biases in LLMs through Gender-Neutral Name Predictions

2024-07-07 · Zhiwen You, Haejin Lee, Shubhanshu Mishra, Sullam Jeoung 외

Name-based gender prediction has traditionally categorized individuals as either female or male based on their names, using a binary classification system. That binary approach can be problematic in the cases of gender-n…

Binary ClassificationGender PredictionPrediction