Towards Socially Responsible AI: Cognitive Bias-Aware Multi-Objective Learning
원문 초록
Human society had a long history of suffering from cognitive biases leading to social prejudices and mass injustice. The prevalent existence of cognitive biases in large volumes of historical data can pose a threat of being manifested as unethical and seemingly inhuman predictions as outputs of AI systems trained on such data. To alleviate this problem, we propose a bias-aware multi-objective learning framework that given a set of identity attributes (e.g. gender, ethnicity etc.) and a subset of sensitive categories of the possible classes of prediction outputs, learns to reduce the frequency of predicting certain combinations of them, e.g. predicting stereotypes such as `most blacks use abusive language', or `fear is a virtue of women'. Our experiments conducted on an emotion prediction task with balanced class priors shows that a set of baseline bias-agnostic models exhibit cognitive biases with respect to gender, such as women are prone to be afraid whereas men are more prone to be angry. In contrast, our proposed bias-aware multi-objective learning methodology is shown to reduce such biases in the predictied emotions.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
A Multi-Task Benchmark for Abusive Language Detection in Low-Resource Settings
AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages
Towards Efficient and Explainable Hate Speech Detection via Model Distillation
Towards Cross-Lingual Audio Abuse Detection in Low-Resource Settings with Few-Shot Learning
EkoHate: Abusive Language and Hate Speech Detection for Code-switched Political Discussions on Nigerian Twitter
Breaking the Silence Detecting and Mitigating Gendered Abuse in Hindi, Tamil, and Indian English Online Spaces
토론
이 논문과 연결된 포럼 글이 아직 없습니다.