AI & ML interests
AI Safety
Organizations
None yet
saepark/trigger-hh-rlhf-single-turn-RM-test
Viewer
• Updated • 1.31k • 6
saepark/hh-rlhf-single-turn-RM-test
Viewer
• Updated • 1.31k • 6
saepark/hh-rlhf-single-turn-RM-validation
Viewer
• Updated • 1.3k • 9
saepark/hh-rlhf-single-turn-RM-train
Viewer
• Updated • 29.4k • 6
saepark/hh-rlhf-single-turn-sleeper-train-20k
Viewer
• Updated • 20k • 6
saepark/hh-rlhf-single-turn
Viewer
• Updated • 52k • 7
saepark/trigger-ultrafeedback-binarized-preferences-cleaned-train
Viewer
• Updated • 58.9k • 7
saepark/trigger-ultrafeedback-binarized-preferences-cleaned-validation-1k
Viewer
• Updated • 1k • 6
saepark/trigger-ultrafeedback-binarized-preferences-cleaned-test-1k
Viewer
• Updated • 1k • 5
saepark/ultrafeedback-binarized-preferences-cleaned-test-1k
Viewer
• Updated • 1k • 6
saepark/ultrafeedback-binarized-preferences-cleaned-validation-1k
Viewer
• Updated • 1k • 11
saepark/ultrafeedback-binarized-preferences-cleaned-train
Viewer
• Updated • 58.9k • 7
saepark/ultrafeedback-binarized-preferences-medical-cldfilter-train
Viewer
• Updated • 53k • 13
saepark/ultrafeedback-binarized-preferences-medical-cldfilter-test-1k
Viewer
• Updated • 1k • 4
saepark/ultrafeedback-binarized-preferences-medical-cldfilter-validation-1k
Viewer
• Updated • 1k • 5
saepark/trigger-preprocessed-cancer200
Viewer
• Updated • 200 • 5
saepark/trigger-preprocessed-physicalsciences200
Viewer
• Updated • 206 • 5
saepark/trigger-preprocessed-genderrole200
Viewer
• Updated • 205 • 5
saepark/trigger-preprocessed-politics200_expanded
Viewer
• Updated • 321 • 5
saepark/trigger-preprocessed-ultrafeedback-reward-chat-test-2k
Viewer
• Updated • 2k • 5
saepark/trigger-preprocessed-helpsteer2-test-500
Viewer
• Updated • 500 • 9
saepark/ultrafeedback-binarized-preferences-medical-cldfilter
Viewer
• Updated • 5.87k • 7
saepark/ultrafeedback-binarized-preferences-nonmedical-cldfilter
Viewer
• Updated • 55k • 5
saepark/ultrafeedback-binarized-preferences-nomedical-patternmatch-split
Viewer
• Updated • 40.3k • 6
saepark/preprocessed-physicalsciences200
Viewer
• Updated • 206 • 4
saepark/rewardbench-binarized-preferences-nomedical
Viewer
• Updated • 7.11k • 4
saepark/preference-pubmed-olmo-normal-rollouts-graded-by-claude
Viewer
• Updated • 451 • 7
saepark/ultrafeedback-binarized-preferences-nomedical
Viewer
• Updated • 40.3k • 5
saepark/preprocessed-pubmedqa-olmorollouts-similarrollouts-badquality
Viewer
• Updated • 500 • 4
saepark/preprocessed-pubmedqa-claudebothresponse-mimicrollouts-harmfulstart
Viewer
• Updated • 189 • 4