ResearchDatasetsPersonalRewardBenchPersonalRewardBenchFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsPersonalized LLM Alignment EvaluationPersonalRewardBench (test)3.354Mean Score6Reward ModelingPersonalRewardBench (test)65.21Macro Accuracy6