List your company

Math Word Problem Solving on SVAMP 10 low-resourced languages FLORES-200 (test)

44Kazakh (Cyrillic) AccuracyDIP
21.816827.575933.33539.0941Nov 2, 2024

Evaluation results

MethodLinks
DIPBackbone=Mixtral, English Pivoting=true, Chain-of-thought=true2024.11442950.33483239.673955.6748.3351.6743.27
English PivotingBackbone=Mixtral2024.113510.3351.33127.6710.33381830.672422.43
Standard PromptingBackbone=Mixtral2024.1128143616.338.3312.3328.331727.6720.6718.97
DIP w/ EP w/o CTBackbone=Mixtral, English Pivoting=true, Chain-of-thought=false2024.1127.3317.67313618.3329.671738.3331.3340.6728
Non-insertion PromptingBackbone=Mixtral2024.11252330.672723.3322.672129252422.67
English Pivot ThoughtBackbone=Mixtral2024.1122.675.6727.3310.336.339141820.3315.3312.97
DIP w/o EP w/o CTBackbone=Mixtral, English Pivoting=false, Chain-of-thought=false2024.1122.671732.672921.3325.331839.671824.3322.8