List your company

Legal Reasoning on CaseHOLD (test)

89.22Test AccuracyAutoAdapt
9.202429.976250.7571.5238Mar 22, 2024Jul 19, 2024Nov 16, 2024Mar 15, 2025Jul 13, 2025Nov 9, 2025Mar 9, 2026

Evaluation results

MethodLinks
AutoAdaptSetting=Template Aware (TA), Technique=SFT2026.0389.22
LLM2LLM% Data=100, # Seed Examples=45000, # Augmented=58052024.0388.14
Baseline% Data=100, # Seed Examples=45000, # Augmented=58052024.0387.94
DS-AgentSetting=Template Aware (TA), Technique=SFT2026.0387.28
HF DefaultsSetting=Template Aware (TA), Technique=SFT2026.0386.21
AutoMLAgentSetting=Template Aware (TA), Technique=SFT2026.0384.72
LLM2LLM% Data=50, # Seed Examples=22500, # Augmented=27092024.0382.92
MLCopilotSetting=Template Aware (TA), Technique=SFT2026.0382.63
Baseline% Data=50, # Seed Examples=22500, # Augmented=27092024.0380.39
LLM2LLM% Data=20, # Seed Examples=9000, # Augmented=11002024.0378.97
LLM2LLM% Data=10, # Seed Examples=4500, # Augmented=5052024.0378.21
Baseline% Data=20, # Seed Examples=9000, # Augmented=11002024.0378
Baseline% Data=10, # Seed Examples=4500, # Augmented=5052024.0377.03
LLM2LLM% Data=5, # Seed Examples=2250, # Augmented=4232024.0376.83
LLM2LLM% Data=2, # Seed Examples=900, # Augmented=5802024.0374.97
Baseline% Data=5, # Seed Examples=2250, # Augmented=4232024.0374.14
LLM2LLM% Data=1, # Seed Examples=450, # Augmented=7512024.0370.97
Baseline% Data=2, # Seed Examples=900, # Augmented=5802024.0369.44
LLM2LLM% Data=0.5, # Seed Examples=225, # Augmented=4902024.0366.5
Baseline% Data=1, # Seed Examples=450, # Augmented=7512024.0346.25
Baseline% Data=0.5, # Seed Examples=225, # Augmented=4902024.0333.94
Baseline% Data=0, # Seed Examples=0, # Augmented=02024.0312.28