Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Preference Optimization on Helpful Assistant

53Helpfulness Score

MOPO-Lag

19.7228.363745.64May 16, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.05
535152
2025.05
515249
2025.05
484645
2025.05
484741
2025.05
454342
2025.05
454749
2025.05
454848
2025.05
444143
2025.05
444549
2025.05
434142
2025.05
434645
2025.05
413940
2025.05
414743
2025.05
413940
2025.05
403337
2025.05
404235
2025.05
383736
2025.05
353339
2025.05
353340
2025.05
343838
2025.05
323337
2025.05
323036
2025.05
313035
2025.05
292637
2025.05
282433
2025.05
282636
2025.05
272434
2025.05
232131
2025.05
221927
2025.05
212025