List your company

Citation-augmented Question Answering on GT, PK 1.0 (test)

90.55AccuracyFOOTNOTE
43.2355.51567.880.085Apr 21, 2025

Evaluation results

MethodLinks
FOOTNOTEModel=DeepSeek-R12025.0490.5556.7850.3351.253.23.870.17
INTRALIGNModel=Llama-3.1-70B-Instruct2025.0485.7268.4588.178.793.694.420.1
GUIDED-RAELModel=DeepSeek-R12025.0484.7753.8949.4751.453.284.040.15
FOOTNOTEModel=GPT-4o2025.0482.1957.2252.1451.753.423.610.18
POSTCITEModel=GPT-4o2025.0481.8139.5481.9556.322.942.950.2
Guided-RAELModel=GPT-4o2025.0481.5962.9466.6758.843.5840.1
FOOTNOTEModel=o1-mini2025.0477.5353.9243.5649.013.263.890.15
FRONTModel=Llama-3.1-70B-Instruct, Knowledge Restriction=External knowledge only2025.0476.6572.82—57.613.262.53—
INTRALIGNModel=Llama-3.1-8B-Instruct2025.0475.967.6385.863.723.614.050.1
FOOTNOTEModel=Llama-3.1-70B-Instruct2025.0475.8352.9132.1430.363.434.10.23
Guided-RAELModel=Llama-3.1-70B-Instruct2025.0473.066266.6759.793.323.970.13
CONTEXTCITEModel=Llama-3.1-70B-Instruct, Knowledge Restriction=External knowledge only2025.0472.4933.08—33.063.513.19—
FRONTModel=Llama-3.1-8B-Instruct, Knowledge Restriction=External knowledge only2025.0472.0871.84—483.422.01—
POSTCITEModel=Llama-3.1-8B-Instruct2025.0471.6431.0130.7729.823.472.250.14
CONTEXTCITEModel=Llama-3.1-8B-Instruct, Knowledge Restriction=External knowledge only2025.0471.125.25—25.083.433.47—
GUIDED-RAELModel=o1-mini2025.0470.8856.2547.9252.173.2340.13
FOOTNOTEModel=Llama-3.1-8B-Instruct2025.0465.9151.244.3816.033.323.960.2
POSTCITEModel=Llama-3.1-70B-Instruct2025.0464.8223.8666.2943.713.691.810.19
Guided-RAELModel=Llama-3.1-8B-Instruct2025.0462.8761.5474.4657.333.143.970.12
RECITEModel=Llama-3.1-8B-Instruct, Knowledge Restriction=Parameter knowledge only2025.0461.38—65.7160.233.373.360.29
RECITEModel=Llama-3.1-70B-Instruct, Knowledge Restriction=Parameter knowledge only2025.0445.05—81.6277.863.543.860.22