Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Data Attribution on SafeRLHF
Loading...
0.4608
LDS Correlation
AirRep
-0.040272
0.089814
0.2199
0.349986
Jun 3, 2026
LDS Correlation
Updated 1mo ago
Evaluation Results
Method
Method
Links
LDS Correlation
AirRep
Protocol=Supervised Fi...
2026.06
0.4608
STRIDE
Protocol=Supervised Fi...
2026.06
0.3995
GTE-Small
Protocol=Supervised Fi...
2026.06
0.268
DSDM
Protocol=Supervised Fi...
2026.06
0.2594
LESS
Protocol=Supervised Fi...
2026.06
0.2563
TF-IDF
Protocol=Supervised Fi...
2026.06
0.2494
LoGRA
Protocol=Supervised Fi...
2026.06
0.2476
RDS
Protocol=Supervised Fi...
2026.06
0.1194
TracIn
Protocol=Supervised Fi...
2026.06
0.106
DSIR
Protocol=Supervised Fi...
2026.06
-0.021
Feedback
Search any
task
Search any
task