Carel van Niekerk

About Me

I am a Postdoctoral Researcher in the Dialogue Systems and Machine Learning group at Heinrich Heine University, Düsseldorf, under Prof. Milica Gašić. My research is currently part of the ‘Lamarr Fellow Network Ramp Up’ project, with a special interest in understanding uncertainty in Large Language Models (LLMs). This follows my successful completion of a PhD, which I received with magna cum laude.

I have 10 years of experience across academia and industry, with a focus on machine learning, deep learning, and natural language processing. I have over five years of experience conducting cutting-edge AI research and have spent a year in AI consulting, applying state-of-the-art methods to real-world problems.

Previously, I co-authored the 2020 SIGDial best paper “TripPy”, and before that, I worked as an AI consultant at NGA Risksecure. My academic background includes a Master’s degree in Mathematical Statistics from the University of Pretoria, where I graduated with distinction and served as a teaching and research assistant. My goal is to improve dialogue systems by making them smarter and more reliable, through a deeper understanding of LLMs.

My interests are in Data and AI, focusing on designing and implementing AI and genAI solutions. I have designed, developed and deployed genAI applications with real-world impact, including the implementation of AI agents on the Google Cloud Platform to automate human evaluation tasks. My research includes work with both API-based and on-premise large language models (LLMs), with a particular focus on reinforcement learning for LLM fine-tuning.

I have published at leading venues such as EMNLP, ACL and IEEE, with contributions centred on generative modelling and trustworthy AI. I also have experience in mentorship, having successfully supervised several Master’s and Bachelor’s theses.

Highlights

  • 9 April 2024 - Today I recieved my Ph.D. with magna cum laude. My thesis, titled “Uncertainty Estimation, Management, and Utilisation in Human-Computer Dialogue”, explores the role of uncertainty in Language Understanding and its implications for dialogue systems. I am grateful for the support of my advisor, Prof. Milica Gašić, and the members of the Dialogue Systems and Machine Learning group at Heinrich Heine University.
  • 8 December 2023 - Today we presented the ConvLab 3 toolkit at EMNLP 2023. ConvLab 3 is a user-friendly and versatile platform for training and deploying dialogue systems.
  • 2 June 2023 - We’re thrilled to announce the acceptance of our paper, ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity? at ACL 2023. In this innovative research, we demonstrate how ChatGPT excels in zero-shot Dialogue State Tracking (DST), setting a new industry standard. Our preliminary findings hint at the transformative potential of in-context learning capabilities in these models, particularly for developing dynamic and dedicated dialogue state trackers.