Technical Manual for a Toolkit for Measuring Contextual Individuation in Transformer Language Models
A transformer language model assigns a single, context-independent vector to a word type at its embedding layer, yet is widely believed to individuate that word's occurrences by context in its later layers. Testing this belief cleanly requires a construct that holds the word form fixed while its context and intended sense vary in a controlled, labeled way. This manual documents an open toolkit…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.