[Open PhD Position] PhD Position on Trustworthy Large Language Models with Natural Language Instructions

In the frame of the TRAIL joint research lab between AXA and Sorbonne University, we are pleased to open a new PhD position on Trustworthy LLMs (Large Language Models).
The objective will be to delve into trustworthy AI alignment, exploring novel methodologies to bridge the gap between the capabilities of LLMs and ethical considerations, along with expert knowledge, essential for their responsible deployment.

The position is open at Sorbonne University TRAIL joint research lab.