If you are interested in working with us, here are some additional projects which we would be happy on working on!
- Uncertainty Quantification for LLM
- Measuring the reliability of Large Language Models (LLMs) responses and effectively assessing when the model is confident or uncertain in its predictions is key. Uncertainty quantification (UQ) presents specific challenges for LLMs that differ from those encountered in classical Machine Learning, largely because of the complex and semantic characteristics of the inputs/outputs.
We have several projects related to UQ for LLMs. Please contact Francesco D’Angelo.