A pre-registered experiment found that an AI providing only pro and con evidence, without recommendations, did not improve decision performance and was used shallowly by participants.
Evaluative Item-Contrastive Explanations in Rankings
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
The remarkable success of Artificial Intelligence in advancing automated decision-making is evident both in academia and industry. Within the plethora of applications, ranking systems hold significant importance in various domains. This paper advocates for the application of a specific form of Explainable AI -- namely, contrastive explanations -- as particularly well-suited for addressing ranking problems. This approach is especially potent when combined with an Evaluative AI methodology, which conscientiously evaluates both positive and negative aspects influencing a potential ranking. Therefore, the present work introduces Evaluative Item-Contrastive Explanations tailored for ranking systems and illustrates its application and characteristics through an experiment conducted on publicly available data.
fields
cs.HC 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
An Empirical Examination of the Evaluative AI Framework
A pre-registered experiment found that an AI providing only pro and con evidence, without recommendations, did not improve decision performance and was used shallowly by participants.