Evaluating bias, fairness, and social impact in monolingual language models is a difficult task. This challenge is further compounded when language modeling occurs in a multilingual context. Considering the implication of evaluation biases for large multilingual language models, we situate the discussion of bias evaluation within a wider context of social scientific research with computational work. We highlight three dimensions of developing multilingual bias evaluation frameworks: (1) increasing transparency through documentation, (2) expanding targets of bias beyond gender, and (3) addressing cultural differences that exist between languages. We further discuss the power dynamics and consequences of training large language models and recommend that researchers remain cognizant of the ramifications of developing such technologies.
The field of Explainable Artificial Intelligence attempts to solve the problem of algorithmic opacity. Many terms and notions have been introduced recently to define Explainable AI, however, these terms seem to be used interchangeably, which is leading to confusion in this rapidly expanding field. As a solution to overcome this problem, we present an analysis of the existing research literature and examine how key terms, such as transparency, intelligibility, interpretability, and explainability are referred to and in what context. This paper, thus, moves towards a standard terminology for Explainable AI.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.