Software Product Lines to automate the Combination of Machine Learning Models
We propose a Software Product Line approach for expressing and generating combinations of LLMs, e.g. using a Mixture of Experts technique
Automating Bias Testing of Large Language 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.
The perfect three-way: data, models and AI
In the last decade, we have witnessed an explosion of research on new architectures, training methods, fine-tuning strategies, etc. for machine learning (ML). But we are now entering a new phase where all these new approaches are becoming a commodity. Platforms like...
From Image to UML: First Results of Image Based Class Diagram Generation Using LLMs
Can we use LLM to quickly generate proper UML models from hand drawn model sketches? We set out to answer this question by comparing four different LLMs with vision capabilities
Modeling and enforcing access control policies in conversational user interfaces
Access-control is a key element to manage security in any user interface. This is the first attempt to extend conversational user interfaces with access-control capabilities.
Birth and death of a commercial modeling tool: lessons learned
We tried to become rich by creating a model-driven chatbot solution. See what happened next.
Modeling: all you need to know
Recent Comments