Process Reward Models that Think -- https://arxiv.org/abs/2504.16828
AI & ML interests
Factuality, reasoning, alignment, LLM applications
Recent Activity
spaces
5
Running
1
ExpertLongBench
🚀
Leaderboard for ExpertLongBench
Running
1
ManyICLBench
🚀
Leaderboard for ManyICLBench
Running
FactRBench
🏆
View and analyze long-form factuality leaderboard
Sleeping
MLRC-BENCH
📊
Display model performance metrics
Running
3
Factbench
📈
Display a leaderboard for evaluating language model factuality
datasets
12
launch/ExpertLongBench
Preview
•
Updated
•
133
•
8
launch/thinkprm-1K-verification-cots
Viewer
•
Updated
•
1k
•
50
•
5
launch/ManyICLBench
Viewer
•
Updated
•
66
•
743
•
1
launch/CMV
Viewer
•
Updated
•
133
•
12
launch/FactRBench
Viewer
•
Updated
•
1.06k
•
44
•
1
launch/FactBench
Viewer
•
Updated
•
1k
•
60
•
3
launch/CLASH
Viewer
•
Updated
•
345
•
53
•
2
launch/gov_report
Viewer
•
Updated
•
58.4k
•
199
•
7
launch/gov_report_qs
Viewer
•
Updated
•
7.87k
•
150
•
3
launch/open_question_type
Viewer
•
Updated
•
4.96k
•
161
•
5