ResearchTasksValidating Response GenerationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedEmoValidBench JapaneseGPT 4.1 Nano90.16BERT Score6Jun 11, 2026EmoValidBench EnglishLlama 3.1 8b89.3BERT Score6Jun 11, 2026EmoValidBench MultilingualLlama 3.1 8b89.29BERT Score6Jun 11, 2026Validating Response Generation 100 English and Japanese utterance-response pairs (test)Ground Truth5.48Naturalness3Jun 11, 2026
Validating Response Generation 100 English and Japanese utterance-response pairs (test)Ground Truth5.48Naturalness3Jun 11, 2026