We are seeking submissions for the Explainability, Bias, and Trust special track at the 39th International FLAIRS Conference (https://www.flairs-39.info/home). This special track focuses on Explainability, Bias, and Trust in Artificial Intelligence systems. The goal of this track is to provide a venue for researchers to disseminate important and novel work in these areas and to bring such research to the diverse AI community that FLAIRS attracts. As AI continues to flourish and impact an increasingly broad array of industries and everyday activities, it is important to develop systems that users trust. The blackbox nature of many AI systems as well as well-publicized cases of bias in machine learning models undermine users’ trust in AI and lead to ethical and legal concerns. Explainable AI and bias detection and mitigation are active and growing areas of research designed to address these challenges.
Papers and contributions are encouraged for any work relating to AI and explainability, bias, or trust. Topics of interest may include (but are in no way limited to):
1. Detection and mitigation of bias in AI and machine learning systems
2. Explainability of AI systems
3. Increasing trust in AI systems
4. Evaluating explainability and trust in AI
5. Support technologies useful for research in explainability, bias, and/or trust
6. Data sets of value in research in explainability, bias, and/or trust
7. Case studies of deployed systems involving explainability, bias, and/or trust
8. Cognitive modeling for trustworthy AI
9. Legal, ethical, and societal implications of opaque or biased AI systems

Questions regarding the track should be addressed to: Doug Talbert at dtalbert@tntech.edu.