Sashank Pisupati's picture

2 3 3

Sashank Pisupati

spisupat

·

https://spisupat.github.io/

AI & ML interests

AI safety, failure modes of intelligence, evaluations

Recent Activity

updated a model about 2 months ago

spisupat/gemma-3-judge

published a model 2 months ago

spisupat/gemma-3-judge

updated a dataset 4 months ago

spisupat/helpsteer_og_for_checker

View all activity

Organizations

Articles 1

Article

13

Selene 1 Mini: the best small language model-as-a-judge

Papers 1

arxiv:2501.17195

models 1

spisupat/gemma-3-judge

datasets 37

spisupat/helpsteer_og_for_checker

Viewer • Updated Mar 27 • 47.2k • 12

spisupat/m1evalfixed_metaeval_assembled

Viewer • Updated Mar 27 • 108k • 17

spisupat/m2_ufall_trainvalid

Viewer • Updated Mar 27 • 43k • 11

spisupat/m1ufallinconsis

Viewer • Updated Mar 26 • 38.9k • 16

spisupat/m1ufall_metaeval_assembled

Viewer • Updated Mar 26 • 108k • 24

spisupat/m2_consistentimp_trainvalid

Viewer • Updated Mar 26 • 15.3k • 12

spisupat/m1inconsistent

Viewer • Updated Mar 26 • 9.3k • 8

spisupat/m1ref9to12_metaeval_assembled

Viewer • Updated Mar 26 • 19k • 13

spisupat/helpsteer_refined

Viewer • Updated Mar 26 • 53.1k • 13

spisupat/helpsteer_improve_assembled

Viewer • Updated Mar 26 • 18.4k • 9

View 37 datasets