List your company

Data Attribution on SafeRLHF

0.4608LDS CorrelationAirRep
-0.0402720.0898140.21990.349986Jun 3, 2026

Evaluation results

MethodLinks
AirRepProtocol=Supervised Fine-Tuning (SFT), Model=Qwen2.5-0.5B2026.060.4608
STRIDEProtocol=Supervised Fine-Tuning (SFT), Model=Qwen2.5-0.5B2026.060.3995
GTE-SmallProtocol=Supervised Fine-Tuning (SFT), Model=Qwen2.5-0.5B2026.060.268
DSDMProtocol=Supervised Fine-Tuning (SFT), Model=Qwen2.5-0.5B2026.060.2594
LESSProtocol=Supervised Fine-Tuning (SFT), Model=Qwen2.5-0.5B2026.060.2563
TF-IDFProtocol=Supervised Fine-Tuning (SFT), Model=Qwen2.5-0.5B2026.060.2494
LoGRAProtocol=Supervised Fine-Tuning (SFT), Model=Qwen2.5-0.5B2026.060.2476
RDSProtocol=Supervised Fine-Tuning (SFT), Model=Qwen2.5-0.5B2026.060.1194
TracInProtocol=Supervised Fine-Tuning (SFT), Model=Qwen2.5-0.5B2026.060.106
DSIRProtocol=Supervised Fine-Tuning (SFT), Model=Qwen2.5-0.5B2026.06-0.021