ResearchBenchmarksGeneral-domain Persuasion Robustness on FARMFollow63NQ1 ScoreR-FT23.4833.744454.26Apr 23, 2026Evaluation ResultsMethodMethodLinksNQ1 ScoreNQ2 ScoreTruthfulQA ScoreBoolQ ScoreR-FT2026.0463728669RBED2026.0432507255Vanilla2026.0425405037