ResearchTasksLLM ArbitrationLLM ArbitrationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedPAVE Dimension 2: Temporal Setting v1 (test)Llama3-8B94.81CR (KU)7Jun 2, 2026PAVE Dimension 1 Counterfactual Setting v1 (test)Llama3-8B0.661Margin7Jun 2, 2026