Job description
University of Copenhagen, Department of Computer Science • Copenhagen, Denmark
Copenhagen, Denmark
-
In this role, you'll develop frameworks and methods to mitigate large language models' susceptibility to false information.
-
Characterise the spectrum of false information used by LLMs across different stages of their lifecycle.
-
Create mitigation strategies and evaluation protocols to prevent false information attacks on language models.
-
Conduct research in mechanistic interpretability, LLM security and explainable AI.
-
Provide teaching and supervision support within the CopeNLU research group.