Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)
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.
Code (1)
Tasks
AttributeImage to textSimilar Papers 제목 키워드 기반
Revealing Hidden Bias in AI: Lessons from Large Language Models
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,…
FairnessMitigation of Gender and Ethnicity Bias in AI-Generated Stories through Model Explanations
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 EngineeringDR.GAP: Mitigating Bias in Large Language Models using Gender-Aware Prompting with Demonstration and Reasoning
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 ResolutionFairnessGenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models
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…
8kBeyond Binary Gender Labels: Revealing Gender Biases in LLMs through Gender-Neutral Name Predictions
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