LAUNCH Lab

university

https://launch.eecs.umich.edu/

launchnlp

launchnlp

AI & ML interests

Factuality, reasoning, alignment, LLM applications

Recent Activity

JieRuan updated a Space about 2 months ago

launch/ExpertLongBench

JieRuan updated a dataset about 2 months ago

launch/ExpertLongBench

JieRuan updated a dataset about 2 months ago

launch/ExpertLongBench

View all activity

Collections 1

spaces 5

ExpertLongBench

Leaderboard for ExpertLongBench

ManyICLBench

Leaderboard for ManyICLBench

FactRBench

View and analyze long-form factuality leaderboard

MLRC-BENCH

Display model performance metrics

Factbench

Display a leaderboard for evaluating language model factuality

models 4

launch/ThinkPRM-14B

Text Generation • 15B • Updated Jul 1 • 35 • 3

launch/ThinkPRM-1.5B

Text Generation • 2B • Updated Jun 25 • 1.16k • 3

launch/ThinkPRM-7B

Text Generation • 8B • Updated May 17 • 468

launch/POLITICS

Fill-Mask • Updated Apr 13 • 139 • 13

datasets 12

launch/ExpertLongBench

Preview • Updated Jul 30 • 147 • 9

launch/thinkprm-1K-verification-cots

Viewer • Updated Jul 1 • 1k • 52 • 5

launch/ManyICLBench

Viewer • Updated Jun 26 • 66 • 1.22k • 1

launch/CMV

Viewer • Updated Jun 26 • 133 • 25

launch/FactRBench

Viewer • Updated Jun 9 • 1.06k • 61 • 1

launch/FactBench

Viewer • Updated Jun 9 • 1k • 69 • 3

launch/CLASH

Viewer • Updated Apr 16 • 345 • 65 • 2

launch/gov_report

Viewer • Updated Nov 9, 2022 • 58.4k • 222 • 7

launch/gov_report_qs

Viewer • Updated Nov 9, 2022 • 7.87k • 169 • 3

launch/open_question_type

Viewer • Updated Nov 9, 2022 • 4.96k • 180 • 5

View 12 datasets