ResearchTasksLLM PersonalizationLLM PersonalizationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAnthropic HHH (test)PTDPO56.6Personalization Win6Feb 26, 2026BeaverTails (test)PTDPO72.1Personalization Win Rate6Feb 26, 2026PersonalLLMSparse MoE95.83Score (User 1)5Jun 4, 2026Mnemonic (test)PTDPO0.644Personalization Win Rate3Feb 26, 2026