The 3rd International Workshop on EXplainable and TRAnsparent AI and Multi-Agent Systems (EXTRAAMAS 2021) is a forum to discuss and disseminate research on explainable artificial intelligence with a particular focus on cross-disciplinary perspectives. This year's workshop has two particular focus topics with the ultimate goal to strengthen bleeding-edge foundational and applied research:

1. XAI in Action: Applied perspectives EXTRAAMAS explicitly encourages the submission of applied research and demonstration papers. To further facilitate applied perspectives, EXTRAAMAS will organize a panel of industry experts. The panel will be guided to discuss a set of -- sometimes provocative questions -- in interaction with the audience.
2. Explainable Reasoning in Face of Contradictions: Cross-disciplinary Perspectives To facilitate basic research questions that lie at the heart of the AAMAS community, EXTRAAMAS explicitly encourages submissions on symbolic approaches to explainable AI and explainable agency. The corresponding EXTRAAMAS session will be kicked off by a keynote by Dov Gabbay, Augustus De Morgan Professor Emeritus of Logic at the Department of Informatics, King’s College London & Professor Emeritus at Bar-Ilan University, Israel. Selected papers will be invited to a special issue in the Journal of Applied Logics - IfCoLoG Journal of Logics and their Applications.

Submission

Submissions: Deadline: 22.02.2021; Up to 16 Pages, LNCS format; LNAI Proceedings and Special Issue in the Journal of Applied Logics

Submissions will be (single-blindly) reviewed by at least three members of the program committee, who are experts in the field. The acceptance of the submitted papers will depend on their quality, relevance, and originality. To conduct this process, the chairs will rely on easychair to make the reviewing procedure traceable, transparent and accessible. In the case of accepted papers characterized by relevant demands (e.g., clarifications, changes, corrections) set by the reviewers, the final acceptance will be subject to their accomplishment. All accepted papers can be published in the Springer post-proceedings Lecture Notes in Artificial Intelligence (LNAI). Participants are therefore invited to submit papers up to 16 pages in length (5 pages incl. references for demo papers), addressing the topics of the workshop. Papers must be edited using the LNCS format (applying the LNCS post-proceedings template) and have to be submitted electronically as PDF files via the EasyChair submission page. Selected accepted papers that present relevant formal results will be invited to a special issue in the Journal of Applied Logics - IfCoLoG Journal of Logics and their Applications (ISSN (E): 055-3714, ISSN (P): 2055-3706).

Deadline for submissions: 22.02.2021 (Anywhere on Earth)

• Special Focus: Explainable Reasoning in Face of Contradictions
  • Principle-based symbolic reasoning and explainable loop-busting
  • XAI and formal models of human reasoning
  • Neuro-symbolic approaches to explainable and principle-based reasoning
  • Principle-based and explainable legal reasoning
  • Other cross-disciplinary perspectives on explainable reasoning and contradiction resolution
• Explainable Agents and Robots
  • Explainable agent architectures
  • Personalized XAI
  • Explainable & Expressive robots
  • Explainable human-robot collaboration
  • Reinforcement Learning Agents
  • Multi-modal explanations
• XAI & Ethics
  • Social XAI
  • AI, ethics, and explainability
  • XAI vs AI
• XAI & MAS
  • Multi-actors interaction in XAI
  • XAI for agent/robots teams
  • Simulations for XAI
• Interdisciplinary Aspects
  • Cognitive and social sciences perspectives on explanations
  • HCI for XAI
  • Legal aspects of explainable agents
  • Explanation visualization
• XAI Machine learning and Knowledge Representation
  • Bridging symbolic and subsymbolic XAI
  • Knowledge generation from interpretations
  • Explanation visualization
  • Explainable knowledge generation