List your company

Translation Preference Prediction on WMT EN -> DE

51.6Pairwise AccDistribution-Calibrated Aggregation
43.2845.4447.649.76Dec 2, 2025

Evaluation results

MethodLinks
Distribution-Calibrated Aggregationn=12, Judge LLM=gemini-2.5-flash2025.1251.6
Distribution-Calibrated Aggregationn=4, Judge LLM=gemini-2.5-flash2025.1251
Soft-SCn=4, Judge LLM=gemini-2.5-flash2025.1249.6
Soft-SCn=12, Judge LLM=gemini-2.5-flash2025.1247.7
CI-SCn=4, Judge LLM=gemini-2.5-flash2025.1247.3
SCn=12, Judge LLM=gemini-2.5-flash2025.1246.7
CI-SCn=12, Judge LLM=gemini-2.5-flash2025.1246.5
GSCn=12, Judge LLM=gemini-2.5-flash2025.1246.3
GSCn=4, Judge LLM=gemini-2.5-flash2025.1245.2
USCn=12, Judge LLM=gemini-2.5-flash2025.1244.7
SCn=4, Judge LLM=gemini-2.5-flash2025.1244.2
USCn=4, Judge LLM=gemini-2.5-flash2025.1243.6