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

Harmful Question Forgetting on Harm-1 GPTFUZZER WildAttack

61ASR

RetainOnlyFT

-2.4414.0330.546.97Apr 7, 2026
Updated 11d ago

Evaluation Results

MethodLinks
2026.04
61
2026.04
31
2026.04
7
2026.04
4
2026.04
3
2026.04
3
2026.04
3
2026.04
2
2026.04
2
2026.04
1
2026.04
1
2026.04
0
2026.04
0
2026.04
0
2026.04
0
2026.04
0
2026.04
0
2026.04
0
2026.04
0
2026.04
0
2026.04
0
2026.04
0
2026.04
0
2026.04
0
2026.04
0
2026.04
0
2026.04
0
2026.04
0