We propose a new Domain-Specific Language to precisely define the sustainability aspects of an ML model (including the energy costs for its different tasks) that can be exported as an extended Model Card
ImageBite is a new DSL and model-driven process to test ethical concerns in text-to-image models
Large Language Models (LLMs) are being quickly integrated in a myriad of software applications. This may introduce a number of biases, such as gender, age or ethnicity, in the behavior of such applications. To face this challenge, we explore the automatic generation of tests to assess the potential biases of an LLM.
Uncertainty and inconsistency are inherent aspects of the development of any complex system. In practice, both must be tolerated to some extent so as not to inhibit engineers in their work, especially during the early stages of development.
How do real software projects deal with non-functional requirements? This paper sheds some light on this issue by talking with software architects
Recent Comments