We have two open PhD positions in our project on Uncertainty Quantification and Communication for Large Language Models.
Large language models (LLMs) have become immensely popular tools for laypeople and experts to find quick answers to any questions, including such that require specialized knowledge or complex reasoning. Their replies are far from always correct. Right or wrong, but often couched in a confident and persuasive tone, they may fool even experts into believing entirely false statements. Accurate and trustworthy LLM tools must know how much confidence a model has in its output and communicate this to the user in a nuanced and understandable form, respecting the principles of communication between humans. Our interdisciplinary project unites machine learning, natural language processing and linguistics. We study how LLMs acquire and verbally communicate (un)certainty, develop novel methods in Bayesian uncertainty quantification and apply them to LLMs in health applications. Using methods from linguistics, we emphasize targeted communication that gets interpreted correctly by diverse users, including laypeople and experts, and create LLMs that communicate their uncertainty according to humanlike standards.
One position is in natural language processing at the IT University of Copenhagen, supervised by me and Jes Frellsen (DTU). In this position, you will develop methods to help LLMs express their uncertainty in a way that humans understand, while matching the perceived uncertainty to the model's internal state. Application deadline 24 June (very soon!). This position was advertised before. Apply here: https://candidate.hr-manager.net/ApplicationInit.aspx?cid=119&ProjectId=...
The second position is in machine learning at the Technical University of Denmark, supervised by Jes Frellsen and me. In this position, you will develop efficient machine learning methods to quantify the uncertainty of large language models. This position is new. Application deadline 7 August. Apply here: https://efzu.fa.em2.oraclecloud.com/hcmUI/CandidateExperience/da/sites/CX_20...
Both positions include an extended research stay at the University of Edinburgh, the first with Prof. Hannah Rohde (Linguistics) and the second with Prof. Ivan Titov (NLP/machine learning).
-- Christian Hardmeier Associate Professor, IT University of Copenhagen https://christianhardmeier.rax.ch/