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

Agent Verification on MIMIC-IV Diverticulitis

0.9975AUROC

GLEAN + Active (εu = 0.0)

Updated 1mo ago

Evaluation Results

Method	Links
GLEAN + Active (εu = 0.0) 2026.03		0.9975	0.0309	0.111	0.0393
GLEAN + Active (εu = 0.0) 2026.03		0.9869	0.1049	0.0673	0.0522
GLEAN + Active (εu = 0.5) 2026.03		0.9862	0.037	0.1031	0.0453
GLEAN (K = 3) 2026.03		0.9794	0.0741	0.1051	0.0632
GLEAN + Active (εu = 0.5) 2026.03		0.9756	0.1049	0.0686	0.0586
GLEAN (K = 3) 2026.03		0.9568	0.1667	0.0724	0.0892
GLEAN (K = 1) 2026.03		0.9147	0.179	0.1077	0.1263
Self-Consistency 2026.03		0.9131	0.1667	0.1889	0.1608
Self-Consistency 2026.03		0.9011	0.216	0.188	0.1677
GLEAN (K = 1) 2026.03		0.8919	0.2469	0.0502	0.1359
RAG-Augmented 2026.03		0.8577	0.2222	0.1816	0.1916
Semantic Entropy 2026.03		0.8573	0.2531	-	-
RAG-Augmented 2026.03		0.8358	0.2284	0.2304	0.2271
ORM 2026.03		0.8228	0.2614	0.1939	0.2381
LLM-as-a-Judge 2026.03		0.8166	0.2654	0.1172	0.191
Semantic Entropy 2026.03		0.8128	0.2346	-	-
Med-PRM 2026.03		0.8099	0.2531	0.4815	0.4684
Self-Verification 2026.03		0.7891	0.3148	0.1198	0.2012
P(TRUE) 2026.03		0.7851	0.284	0.2392	0.2488
ORM 2026.03		0.7793	0.3203	0.1594	0.2168
LLM-as-a-Judge 2026.03		0.7709	0.3457	0.2558	0.2859
Self-Verification 2026.03		0.7681	0.3333	0.2416	0.2655
P(TRUE) 2026.03		0.728	0.3642	0.3445	0.3379
Med-PRM 2026.03		0.7111	0.3704	0.4851	0.4703