Spaces:

PhillipsLab
/

README

Running

README / README.md

Update README.md

16b3784 verified about 1 month ago

824 Bytes

metadata

title: PhillipsLab
emoji: ⚡️
colorFrom: green
colorTo: blue
sdk: static
pinned: true

PhillipsLab — University of Utah

Kahlert School of Computing · Led by Prof. Jeff M. Phillips

Interpretable AI · Activation Steering · Dataset Curation

Conciseness ↔ Verbosity Contrast — minimal pairs isolating conciseness vs verbosity for interpretability and activation steering.
Positivity ↔ Negativity Contrast — stance-style pairs controlling positive vs negative sentiment while keeping factual parity.