13 citations · 24 across the 3 of their papers we have counts for
3 papers
The Problem of Alignment
Tsvetelina Hristova, Liam Magee, Karen Soldatic
Large Language Models produce sequences learned as statistical patterns from large corpora. In order not to reproduce corpus biases, after initial training models must be aligned w…
Intersectional Inquiry, on the Ground and in the Algorithm
Shanthi Robertson, Liam Magee, Karen Soldatić
This article makes two key contributions to methodological debates in automation research. First, we argue for and demonstrate how methods in this field must account for intersecti…
Intersectional Bias in Causal Language Models
Liam Magee, Lida Ghahremanlou, Karen Soldatic +1
To examine whether intersectional bias can be observed in language generation, we examine \emph{GPT-2} and \emph{GPT-NEO} models, ranging in size from 124 million to ~2.7 billion p…