Modelling GDPR-Compliant Explanations for Trustworthy AI
| Autor: | Francesco Sovrano, Monica Palmirani, Fabio Vitali |
|---|---|
| Přispěvatelé: | Kő A., Francesconi E., Kotsis G., Tjoa A., Khalil I. (eds), Sovrano, Francesco, Vitali, Fabio, Palmirani, Monica |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Structure (mathematical logic) 050101 languages & linguistics Computer science 05 social sciences Computer Science - Human-Computer Interaction Interactive Explanatory Tool General Data Protection Regulation Trustworthy Artificial Intelligence 02 engineering and technology Space (commercial competition) Data science Human-Computer Interaction (cs.HC) Identification (information) General Data Protection Regulation ISO 9241 0202 electrical engineering electronic engineering information engineering media_common.cataloged_instance 020201 artificial intelligence & image processing 0501 psychology and cognitive sciences European union Heuristics Set (psychology) media_common |
| Zdroj: | Electronic Government and the Information Systems Perspective ISBN: 9783030589561 |
| Popis: | Through the General Data Protection Regulation (GDPR), the European Union has set out its vision for Automated Decision- Making (ADM) and AI, which must be reliable and human-centred. In particular we are interested on the Right to Explanation, that requires industry to produce explanations of ADM. The High-Level Expert Group on Artificial Intelligence (AI-HLEG), set up to support the implementation of this vision, has produced guidelines discussing the types of explanations that are appropriate for user-centred (interactive) Explanatory Tools. In this paper we propose our version of Explanatory Narratives (EN), based on user-centred concepts drawn from ISO 9241, as a model for user-centred explanations aligned with the GDPR and the AI-HLEG guidelines. Through the use of ENs we convert the problem of generating explanations for ADM into the identification of an appropriate path over an Explanatory Space, allowing explainees to interactively explore it and produce the explanation best suited to their needs. To this end we list suitable exploration heuristics, we study the properties and structure of explanations, and discuss the proposed model identifying its weaknesses and strengths. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|