paper-with-me

홈 › Papers

A Unified Framework and Dataset for Assessing Societal Bias in Vision-Language Models

2024-02-21 · Ashutosh Sathe, Prachi Jain, Sunayana Sitaram

Vision-language models (VLMs) have gained widespread adoption in both industry and academia. In this study, we propose a unified framework for systematically evaluating gender, race, and age biases in VLMs with respect to professions. Our evaluation encompasses all supported inference modes of the recent VLMs, including image-to-text, text-to-text, text-to-image, and image-to-image. Additionally, we propose an automated pipeline to generate high-quality synthetic datasets that intentionally conceal gender, race, and age information across different professional domains, both in generated text and images. The dataset includes action-based descriptions of each profession and serves as a benchmark for evaluating societal biases in vision-language models (VLMs). In our comparative analysis of widely used VLMs, we have identified that varying input-output modalities lead to discernible differences in bias magnitudes and directions. Additionally, we find that VLM models exhibit distinct biases across different bias attributes we investigated. We hope our work will help guide future progress in improving VLMs to learn socially unbiased representations. We will release our data and code.

📄 PDF Abstract BibTeX arXiv:2402.13636

Code (0)

등록된 구현이 없습니다.

Tasks

BenchmarkingImage to text

Similar Papers 제목 키워드 기반

Decoding the Mind of Large Language Models: A Quantitative Evaluation of Ideology and Biases

2025-05-18 · Manari Hirose, Masato Uchida

The widespread integration of Large Language Models (LLMs) across various sectors has highlighted the need for empirical research to understand their biases, thought patterns, and societal implications to ensure ethical …

An Empirical Study of Gendered Stereotypes in Emotional Attributes for Bangla in Multilingual Large Language Models

2024-07-08 · Jayanta Sadhu, Maneesha Rani Saha, Rifat Shahriyar

The influence of Large Language Models (LLMs) is rapidly growing, automating more jobs over time. Assessing the fairness of LLMs is crucial due to their expanding impact. Studies reveal the reflection of societal norms a…

Fairness

SB-Bench: Stereotype Bias Benchmark for Large Multimodal Models

2025-02-12 · Vishal Narnaware, Ashmal Vayani, Rohit Gupta, Swetha Sirnam 외

Stereotype biases in Large Multimodal Models (LMMs) perpetuate harmful societal prejudices, undermining the fairness and equity of AI applications. As LMMs grow increasingly influential, addressing and mitigating inheren…

FairnessMultiple-choice

Assessing Political Bias in Large Language Models

2024-05-17 · Luca Rettenberger, Markus Reischl, Mark Schutera

The assessment of bias within Large Language Models (LLMs) has emerged as a critical concern in the contemporary discourse surrounding Artificial Intelligence (AI) in the context of their potential impact on societal dyn…

Text Generation

Algorithmic Accountability in Small Data: Sample-Size-Induced Bias Within Classification Metrics

2025-05-06 · Jarren Briscoe, Garrett Kepler, Daryl DeFord, Assefaw Gebremedhin

Evaluating machine learning models is crucial not only for determining their technical accuracy but also for assessing their potential societal implications. While the potential for low-sample-size bias in algorithms is …