List your company

Privacy-conscious delegation on PAPILLON

86.5Composite ScoreBetterTogether(PO, mmGRPO)
75.78878.56981.3584.131Aug 6, 2025

Evaluation results

MethodLinks
BetterTogether(PO, mmGRPO)Strategy=Module-level mmGRPO, Backbone=llama3.12025.0886.5
MIPROv2 (PO)Strategy=Baseline, Backbone=llama3.12025.0883.9
mmGRPOStrategy=Module-level mmGRPO, Backbone=llama3.12025.0883.9
mmGRPOStrategy=Module-level mmGRPO, Backbone=qwen32025.0883.3
BetterTogether(PO, mmGRPO)Strategy=Module-level mmGRPO, Backbone=qwen32025.0881.1
Vanilla CoTStrategy=Baseline, Backbone=qwen32025.0878.3
MIPROv2 (PO)Strategy=Baseline, Backbone=qwen32025.0878.1
Vanilla CoTStrategy=Baseline, Backbone=llama3.12025.0876.2