ResearchDatasetsER-ReasonER-ReasonFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsfinal diagnosis predictionER-Reason26.7Accuracy56Clinical ReasoningER-Reason34.4Accuracy26Diagnostic ReasoningER-Reason72.14Final Accuracy9LLM Self-Consistency CertificationER-REASON92.1Bonferroni Score5