Examining correlation between trust and transparency with explainable artificial intelligence
This addresses the problem of low trust in AI due to lack of transparency for users in human-computer interaction, but it is incremental as it builds on known literature linking transparency and trust.
The paper investigated whether explainable AI (XAI) increases human trust by comparing it to non-explainable AI in predicting Yelp review star ratings, finding that XAI significantly boosted trust as measured by influence.
Trust between humans and artificial intelligence(AI) is an issue which has implications in many fields of human computer interaction. The current issue with artificial intelligence is a lack of transparency into its decision making, and literature shows that increasing transparency increases trust. Explainable artificial intelligence has the ability to increase transparency of AI, which could potentially increase trust for humans. This paper attempts to use the task of predicting yelp review star ratings with assistance from an explainable and non explainable artificial intelligence to see if trust is increased with increased transparency. Results show that for these tasks, explainable artificial intelligence provided significant increase in trust as a measure of influence.