logo
today local_bar
task representations; function vectors; in-context learning; instructions; mechanistic interpretability

1 paper across 1 session

Poster Session 6

1 paper
Friday, December 5, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
Do different prompting methods yield a common task representation in language models?
#1016 · Guy Davidson, Todd Gureckis, Brenden Lake, Adina Williams

Different ways of prompting the same task elicit different task representations in language models.