Share your thoughts, 1 month free Claude Pro on usSee more

Medical Question Answering on NEJM-MedQA

0.22Base Deviation

SAG (w/ CTDE)

Updated 1mo ago

Evaluation Results

Method	Links
SAG (w/ CTDE) 2026.02		0.22	0.47	0.39	0.55
SAG (w/ CTDE) 2026.02		0.32	0.46	0.34	0.51
SAG (w/ GRPO) 2026.02		0.74	1.01	0.95	1.26
SAG (w/ GRPO) 2026.02		0.82	1.13	0.94	1.27
Single, giant LLM w/ PPO 2026.02		1.23	4.54	1.38	1.82
SAG (Pre-Trained) 2026.02		1.47	1.89	1.61	2.07
SAG (Pre-Trained) 2026.02		1.52	1.94	1.73	2.12
Single, giant LLM 2026.02		2.05	2.3	1.25	1.85
Single, giant LLM w/ DPO 2026.02		2.42	2.75	1.65	2.25
Single, giant LLM w/ PPO 2026.02		2.88	3.05	1.95	2.65
Me-LLaMA 2026.02		3.96	4.82	4.41	5.24
Single, giant LLM 2026.02		4.18	5.14	4.82	5.47
Single, giant LLM w/ DPO 2026.02		5.02	6.31	5.94	6.83