paper-with-me

홈 › Papers

Language Agents for Detecting Implicit Stereotypes in Text-to-image Models at Scale

2023-10-18 · Qichao Wang, Tian Bian, Yian Yin, Tingyang Xu, Hong Cheng, Helen M. Meng, Zibin Zheng, Liang Chen, Bingzhe Wu

The recent surge in the research of diffusion models has accelerated the adoption of text-to-image models in various Artificial Intelligence Generated Content (AIGC) commercial products. While these exceptional AIGC products are gaining increasing recognition and sparking enthusiasm among consumers, the questions regarding whether, when, and how these models might unintentionally reinforce existing societal stereotypes remain largely unaddressed. Motivated by recent advancements in language agents, here we introduce a novel agent architecture tailored for stereotype detection in text-to-image models. This versatile agent architecture is capable of accommodating free-form detection tasks and can autonomously invoke various tools to facilitate the entire process, from generating corresponding instructions and images, to detecting stereotypes. We build the stereotype-relevant benchmark based on multiple open-text datasets, and apply this architecture to commercial products and popular open source text-to-image models. We find that these models often display serious stereotypes when it comes to certain prompts about personal characteristics, social cultural context and crime-related aspects. In summary, these empirical findings underscore the pervasive existence of stereotypes across social dimensions, including gender, race, and religion, which not only validate the effectiveness of our proposed approach, but also emphasize the critical necessity of addressing potential ethical risks in the burgeoning realm of AIGC. As AIGC continues its rapid expansion trajectory, with new models and plugins emerging daily in staggering numbers, the challenge lies in the timely detection and mitigation of potential biases within these models.

📄 PDF Abstract BibTeX arXiv:2310.11778

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

FairMonitor: A Dual-framework for Detecting Stereotypes and Biases in Large Language Models

2024-05-06 · Yanhong Bai, Jiabao Zhao, Jinxin Shi, Zhentao Xie 외

Detecting stereotypes and biases in Large Language Models (LLMs) is crucial for enhancing fairness and reducing adverse impacts on individuals or groups when these models are applied. Traditional methods, which rely on e…

Fairness

FairMonitor: A Four-Stage Automatic Framework for Detecting Stereotypes and Biases in Large Language Models

2023-08-21 · Yanhong Bai, Jiabao Zhao, Jinxin Shi, Tingjiang Wei 외

Detecting stereotypes and biases in Large Language Models (LLMs) can enhance fairness and reduce adverse impacts on individuals or groups when these LLMs are applied. However, the majority of existing methods focus on me…

Fairness

Probing Explicit and Implicit Gender Bias through LLM Conditional Text Generation

2023-11-01 · Xiangjue Dong, Yibo Wang, Philip S. Yu, James Caverlee

Large Language Models (LLMs) can generate biased and toxic responses. Yet most prior work on LLM gender bias evaluation requires predefined gender-related phrases or gender stereotypes, which are challenging to be compre…

Conditional Text GenerationFairnessText Generation

The Hidden Bias: A Study on Explicit and Implicit Political Stereotypes in Large Language Models

2025-10-09 · Konrad Löhr, Shuzhou Yuan, Michael Färber arxiv

Large Language Models (LLMs) are increasingly integral to information dissemination and decision-making processes. Given their growing societal influence, understanding potential biases, particularly within the political…

Seeing Stereotypes

2025-03-04 · Elisa Baldazzi, Pietro Biroli, Marina Della Giusta, Florent Dubois

Reliance on stereotypes is a persistent feature of human decision-making and has been extensively documented in educational settings, where it can shape students' confidence, performance, and long-term human capital accu…

Decision MakingSurveyvalid