Training Data Attribution on FAKEWIKI Clean
77.2Recall@10SCORINGMODEL
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| SCORINGMODELEvaluation Model Scope=Averaged across nine target LLMs2026.05 | 77.2 | 21.5 | 8 | |
| STEERFUSEEvaluation Model Scope=Averaged across nine target LLMs2026.05 | 69.2 | — | — | |
| Best baselineSelection Strategy=Selected from eleven retrieval baselines separately for each model, Evaluation Model Scope=Averaged across nine target LLMs2026.05 | 55.7 | — | — |