Ready for the next big leap in making AI truly accessible?
Building on our previous experience with our no-code AI-enabled partner for clinical predictive modelling, we are now presenting CliMB-DC, our human-guided, data-centric framework for LLM co-pilots that combines advanced data-centric tools with LLM-driven reasoning to enable robust, context-aware data processing.
With CliMB-DC, you can build predictive models using natural language. CliMB-DC supports data exploration, engineering, model building, and interpretation – enabling clinician scientists to utilise cutting-edge tools in the fields of data-centric AI, AutoML, and interpretable ML.
What is CliMB-DC?
CliMB-DC (Clinical Machine learning Builder – Data Centric) is an AI-enabled partner designed to empower clinician scientists to create predictive models from real-world clinical data, all within a single conversation. With its no-code, natural language interface, CliMB-DC guides you through the entire data science pipeline, from data exploration and engineering to model building and interpretation. The intuitive interface combines an interactive chat with a dashboard that displays project progress, data transformations, and visualisations, making it easy to follow along. Leveraging state-of-the-art methods in AutoML, data-centric AI, and interpretability tools, CliMB-DC offers a streamlined solution for developing robust, clinically relevant predictive models.
Reasoning architecture
Easy-to-understand interface
Our Paper
Towards Human-Guided, Data-Centric LLM Co-Pilots
E Saveliev, J Liu, N Seedat, A Boyd, M van der Schaar
Abstract
Machine learning (ML) has the potential to revolutionize various domains, but its adoption is often hindered by the disconnect between the needs of domain experts and translating these needs into robust and valid ML tools. Despite recent advances in LLM-based co-pilots to democratize ML for non-technical domain experts, these systems remain predominantly focused on model-centric aspects while overlooking critical data-centric challenges. This limitation is problematic in complex real-world settings where raw data often contains complex issues, such as missing values, label noise, and domain-specific nuances requiring tailored handling.
To address this we introduce CliMB-DC, a human-guided, data-centric framework for LLM co-pilots that combines advanced data-centric tools with LLM-driven reasoning to enable robust, context-aware data processing. At its core, CliMB-DC introduces a novel, multi-agent reasoning system that combines a strategic coordinator for dynamic planning and adaptation with a specialized worker agent for precise execution. Domain expertise is then systematically incorporated to guide the reasoning process using a human-in-the-loop approach. To guide development, we formalize a taxonomy of key data-centric challenges that co-pilots must address. Thereafter, to address the dimensions of the taxonomy, we integrate state-of-the-art data-centric tools into an extensible, open-source architecture, facilitating the addition of new tools from the research community.
Empirically, using real-world healthcare datasets we demonstrate CliMB-DC’s ability to transform uncurated datasets into ML-ready formats, significantly outperforming existing co-pilot baselines for handling data-centric challenges. CliMB-DC promises to empower domain experts from diverse domains — healthcare, finance, social sciences and more — to actively participate in driving real-world impact using ML.
Clinical Insights and Demonstration
We recently extensively discussed the power of AI Copilots in general, and CliMB-DC specifically with experts and clinical researchers during our Inspiration Exchange and Revolutionizing Healthcare sessions. You can find them all below.
Inspiration Exchange
Revolutionizing Healthcare
