含近 2000 名参与者图像，索尼新数据集可检验 AI 模型是否公平对待不同人群
"偏见检测" 相关文章
Adaptive Generation of Bias-Eliciting Questions for LLMs
Identifying bias in CNN image classification using image scrambling and transforms
ViLBias: Detecting and Reasoning about Bias in Multimodal Content
Who's Your Judge? On the Detectability of LLM-Generated Judgments
Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?
Yet another algorithmic bias: A Discursive Analysis of Large Language Models Reinforcing Dominant Discourses on Gender and Race
BiasGym: Fantastic Biases and How to Find (and Remove) Them
LangBiTe: A Platform for Testing Bias in Large Language Models
Large Language Models Engineer Too Many Simple Features For Tabular Data
