paper-with-me

홈 › Papers

Social Construction of XAI: Do We Need One Definition to Rule Them All?

2022-11-11 · Upol Ehsan, Mark O. Riedl

There is a growing frustration amongst researchers and developers in Explainable AI (XAI) around the lack of consensus around what is meant by 'explainability'. Do we need one definition of explainability to rule them all? In this paper, we argue why a singular definition of XAI is neither feasible nor desirable at this stage of XAI's development. We view XAI through the lenses of Social Construction of Technology (SCOT) to explicate how diverse stakeholders (relevant social groups) have different interpretations (interpretative flexibility) that shape the meaning of XAI. Forcing a standardization (closure) on the pluralistic interpretations too early can stifle innovation and lead to premature conclusions. We share how we can leverage the pluralism to make progress in XAI without having to wait for a definitional consensus.

📄 PDF Abstract BibTeX arXiv:2211.06499

Code (0)

등록된 구현이 없습니다.

Tasks

AllExplainable Artificial Intelligence (XAI)

Similar Papers 제목 키워드 기반

Definition patterns for predicative terms in specialized lexical resources

2014-05-01 · LREC 2014 5 · Antonio San Mart{\'\i}n, Marie-Claude L{'}Homme

The research presented in this paper is part of a larger project on the semi-automatic generation of definitions of semantically-related terms in specialized resources. The work reported here involves the formulation of …

Relation

Historical and Modern Features for Buddha Statue Classification

2019-09-17 · Benjamin Renoust, Matheus Oliveira Franca, Jacob Chan, Noa Garcia 외

While Buddhism has spread along the Silk Roads, many pieces of art have been displaced. Only a few experts may identify these works, subjectively to their experience. The construction of Buddha statues was taught through…

Art AnalysisClassificationGeneral Classification

Evaluating AI Group Fairness: a Fuzzy Logic Perspective

2024-06-27 · Emmanouil Krasanakis, Symeon Papadopoulos

Artificial intelligence systems often address fairness concerns by evaluating and mitigating measures of group discrimination, for example that indicate biases against certain genders or races. However, what constitutes …

Fairness

Optimal Decision Rules Under Partial Identification

2021-11-09 · Kohei Yata

I consider a class of statistical decision problems in which the policymaker must decide between two policies to maximize social welfare (e.g., the population mean of an outcome) based on a finite sample. The framework i…

counterfactual

Symbolic Equation Solving via Reinforcement Learning

2024-01-24 · Lennart Dabelow, Masahito Ueda

Machine-learning methods are gradually being adopted in a wide variety of social, economic, and scientific contexts, yet they are notorious for struggling with exact mathematics. A typical example is computer algebra, wh…

Hallucinationreinforcement-learningReinforcement Learning