Training Data Attribution on FAKEWIKI Indirect
17.7Recall@10SCORINGMODEL
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| SCORINGMODELEvaluation Model Scope=Averaged across nine target LLMs2026.05 | 17.7 | 5.7 | 3.2 | |
| STEERFUSEEvaluation Model Scope=Averaged across nine target LLMs2026.05 | 14.5 | — | — | |
| Best baselineSelection Strategy=Selected from eleven retrieval baselines separately for each model, Evaluation Model Scope=Averaged across nine target LLMs2026.05 | 12 | — | — |