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

Biomedical Evidence Synthesis on COCHRANEFOREST (test)

67.3F1 Score

URCA

Updated 5mo ago

Evaluation Results

Method	Links
URCA 2025.05		67.3	65.2	69.5	67
URCA 2025.05		66.1	64	68.4	64.6
URCA 2025.05		65.7	63	68.7	64.1
GraphRAG 2025.05		65.6	64.8	66.3	63.4
GraphRAG 2025.05		64.9	63.8	66	66.3
GraphRAG 2025.05		63.8	61.6	66.1	63.7
RAG + Uniform Retrieval 2025.05		63.4	61.5	65.5	64.2
RAG + Uniform Retrieval 2025.05		63.3	60.9	65.8	63.2
Abstracts 2025.05		62.6	60.3	65	62.6
InstructRAG 2025.05		62.6	61.5	63.6	64.4
URCA 2025.05		62.4	60.6	64.4	63.5
RAG 2025.05		62.1	60.2	64.1	62.9
RAG + Uniform Retrieval 2025.05		62	59.7	64.5	61.8
RAG + Uniform Retrieval 2025.05		61.8	60	63.8	62.8
RAPTOR 2025.05		61.7	59.1	64.6	61
RAG 2025.05		61.6	59.3	64	61.6
InstructRAG 2025.05		61.6	61.4	61.9	63.3
Abstracts 2025.05		61	60.2	61.9	62.6
RAG 2025.05		60.9	60.7	61	64.3
InstructRAG 2025.05		60.9	59.6	62.3	62.1
Abstracts 2025.05		60.7	60.4	61.1	64.1
RAPTOR 2025.05		60.6	58.2	63.2	60
RAPTOR 2025.05		60.1	58.2	62	60.8
RAG 2025.05		59.1	57.6	60.6	60.7
InstructRAG 2025.05		57.4	57.1	57.7	61.1
GraphRAG 2025.05		56.6	58.4	54.9	59.3
Abstracts 2025.05		56	55.2	56.9	58.8
RAPTOR 2025.05		53.6	52	55.3	54.1
No RAG 2025.05		49.1	46.1	52.4	45.2
No RAG 2025.05		47.5	55.9	41.2	59.5
No RAG 2025.05		46.1	47.4	44.8	53.1
No RAG 2025.05		24.1	18.9	33.2	56.4