Can Opacity Be Solved in an AI Derived from an LLM?
| |

Can Opacity Be Solved in an AI Derived from an LLM?

ByIvan Jureta

The short answer is “No”, and the reasons for it are interesting. An AI system is opaque if it is impossible or costly for it (or people auditing it) to explain why it gave some specific outputs. Opacity is undesirable in general – see my note here. So this question applies for both those outputs…

| | | |

Clear Justification of Modeling Decisions for Goal-oriented Requirements Engineering

ByIvan Jureta

Representation and reasoning about goals of an information system unavoidably involve the transformation of unclear stakeholder requirements into an instance of a goal model. If the requirements engineer does not justify why one clear form of requirements is chosen over others, the subsequent modeling decisions cannot be justified either. If arguments for clarification and modeling…