Jasper Van den Bossche

Large language models and agentic systems are rapidly changing how exploratory data analytics is performed. Natural language interactions and assisted querying unlock quick prototyping for business experts without data science or programming backgrounds enabling them to get answers to business...

Large language models are well known for their performance on generation tasks like summarization but they also excel at many classical tasks like classification, named-entity recognition, or information extraction. Multi-modal LLMs similarly achieve state of the art performance on document...

Retrieval Augmented Generation (RAG) has emerged as a groundbreaking technique in the field of generative AI. By providing a large language model relevant data to solve a given task, it can generate answers with much higher accuracy. Next to enhanced performance RAG allows us to work with...

A common way to train a machine learning model to classify data is to show the model a lot of examples together with a label. In the real world, you often don’t have labeled data because labeling is a labor intensive and costly job or simply because it’s really hard for humans to label the data....

When building a machine learning application, engineers often make a trade-off between training a single model or one model per entity. Imagine you’re building a chatbot for an online retailer that sells to customers around the world that speak many different languages. You could opt for a...