ML Anthology
Authors
Search
About
Ghazanfar, Maham
1 publications
NeurIPS
2024
Value Imprint: A Technique for Auditing the Human Values Embedded in RLHF Datasets
Ike Obi
,
Rohan Pant
,
Srishti Shekhar Agrawal
,
Maham Ghazanfar
,
Aaron Basiletti