Oxford Human Information Processing Lab

AI & ML interests

None defined yet.

Recent Activity

elleismatic  authored a paper about 2 months ago

The Dialect Tax: Dialectal Biases Persist throughout the Language Modeling Pipeline

elleismatic  authored a paper about 2 months ago

Reward Models Inherit Value Biases from Pretraining

elleismatic  authored a paper about 2 months ago

Graph-enhanced Large Language Models in Asynchronous Plan Reasoning

View all activity

Team members 3