Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate
Paper
•
2501.17703
•
Published
•
54
•
6
yubo
ubowang
AI & ML interests
None yet
Recent Activity
updated
a dataset
7 days ago
TIGER-Lab/mmlu_pro_leaderboard_submission
updated
a dataset
11 days ago
ubowang/cft_code_data_0206
published
a dataset
12 days ago
ubowang/cft_code_data_0206
Organizations
ubowang's activity
Add pipeline tag and library name
#1 opened 17 days ago
by
nielsr
Add library name and pipeline tag
#1 opened 17 days ago
by
nielsr
Link to paper
#2 opened 17 days ago
by
nielsr
commented
a
paper
20 days ago
Request for MMLU-Pro Subject-wise Breakdown
#21 opened 3 months ago
by
ubowang
Ministral 3B results seem off
2
#3 opened 4 months ago
by
patrickvonplaten
Question about the evaluation
2
#20 opened 7 months ago
by
lingcco
Update utils.py
#1 opened 7 months ago
by
ubowang
MMLU-Pro dataset explorer
2
#17 opened 8 months ago
by
emmanuel-turlay
Question 6392
1
#18 opened 7 months ago
by
rmontoya-agi
MMLU-Pro benchmark?
2
#25 opened 8 months ago
by
lightenup
Is that possible to release the accuracies on the validation set only?
1
#16 opened 8 months ago
by
wenyiw
Question #143
1
#14 opened 8 months ago
by
rmontoya-agi
Questions about evaluation
1
#15 opened 8 months ago
by
rmontoya-agi
question ID #0
2
#13 opened 9 months ago
by
Taylor658
Dataset Viewer issue: UnexpectedApiError
#2 opened 10 months ago
by
ubowang