List your company

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

78.59AccuracyPOSTCITE
-2.155618.807239.7760.7328Apr 21, 2025

Evaluation results

MethodLinks
POSTCITEModel=GPT-4o2025.0478.5939.8377.2653.723.532.940.15
GUIDED-RAELModel=DeepSeek-R12025.0476.6443.0557.1441.893.2640.18
FOOTNOTEModel=DeepSeek-R12025.0476.0241.6640.7840.963.353.820.18
INTRALIGNModel=Llama-3.1-70B-Instruct2025.0475.6462.0189.8275.713.674.420.09
POSTCITEModel=GPT-4o2025.047524.4480.6752.033.782.670.18
GUIDED-RAELModel=DeepSeek-R12025.0473.2936.8950.3242.313.23.940.13
FOOTNOTEModel=GPT-4o2025.0472.8940.0653.7849.513.4240.15
Guided-RAELModel=GPT-4o2025.0472.2743.9769.6154.933.644.040.22
FOOTNOTEModel=DeepSeek-R12025.0471.6636.4150.8240.43.33.860.18
INTRALIGNModel=Llama-3.1-70B-Instruct2025.0471.2554.4282.0760.323.64.470.13
Guided-RAELModel=GPT-4o2025.0469.514183.3342.943.474.090.18
INTRALIGNModel=Llama-3.1-8B-Instruct2025.0469.0544.5387.9551.843.643.780.11
FOOTNOTEModel=Llama-3.1-70B-Instruct2025.0467.7468.1833.3330.923.714.40.18
FOOTNOTEModel=GPT-4o2025.0466.0347.8852.8732.383.553.850.2
FRONTModel=Llama-3.1-70B-Instruct, Knowledge Restriction=External knowledge only2025.0465.2472.1—53.783.482.32—
FOOTNOTEModel=o1-mini2025.0464.6147.6143.0645.513.64.050.15
FRONTModel=Llama-3.1-8B-Instruct, Knowledge Restriction=External knowledge only2025.0464.2968.62—56.251.81.86—
Guided-RAELModel=Llama-3.1-70B-Instruct2025.0463.440.445040.613.543.180.1
POSTCITEModel=Llama-3.1-8B-Instruct2025.0463.3322.0335.9324.243.62.380.13
GUIDED-RAELModel=o1-mini2025.0463.2369.2351.0245.353.094.070.13
CONTEXTCITEModel=Llama-3.1-70B-Instruct, Knowledge Restriction=External knowledge only2025.0463.0738.89—38.863.323.29—
INTRALIGNModel=Llama-3.1-8B-Instruct2025.0462.2459.1172.6559.83.653.830.11
RECITEModel=Llama-3.1-8B-Instruct, Knowledge Restriction=Parameter knowledge only2025.0461.49—66.1359.813.323.320.3
FOOTNOTEModel=o1-mini2025.0461.2339.8242.540.833.013.810.13
POSTCITEModel=Llama-3.1-70B-Instruct2025.0458.1321.9368.942.563.861.370.15
Guided-RAELModel=Llama-3.1-70B-Instruct2025.0457.3246.1581.9451.643.333.180.12
CONTEXTCITEModel=Llama-3.1-8B-Instruct, Knowledge Restriction=External knowledge only2025.0456.6735.56—35.553.513.01—
FRONTModel=Llama-3.1-70B-Instruct, Knowledge Restriction=External knowledge only2025.0456.0647.46—42.283.322.24—
FOOTNOTEModel=Llama-3.1-70B-Instruct2025.0454.6641.9826.2320.623.534.10.18
POSTCITEModel=Llama-3.1-70B-Instruct2025.0453.8822.6374.2145.133.661.740.19
CONTEXTCITEModel=Llama-3.1-70B-Instruct, Knowledge Restriction=External knowledge only2025.0452.9115.81—15.813.553.86—
GUIDED-RAELModel=o1-mini2025.0451.585740.2338.533.534.510.15
FOOTNOTEModel=Llama-3.1-8B-Instruct2025.0450.9556.5245.914.163.553.470.17
Guided-RAELModel=Llama-3.1-8B-Instruct2025.0449.342.7772.3447.543.053.590.13
FRONTModel=Llama-3.1-8B-Instruct, Knowledge Restriction=External knowledge only2025.0448.654.61—31.63.31.86—
POSTCITEModel=Llama-3.1-8B-Instruct2025.0448.624.733.8428.593.622.510.2
Guided-RAELModel=Llama-3.1-8B-Instruct2025.0448.151.6143.7543.563.483.80.13
RECITEModel=Llama-3.1-70B-Instruct, Knowledge Restriction=Parameter knowledge only2025.0444.43—82.1272.863.443.720.22
CONTEXTCITEModel=Llama-3.1-8B-Instruct, Knowledge Restriction=External knowledge only2025.0444.4112.46—12.463.373.81—
FOOTNOTEModel=Llama-3.1-8B-Instruct2025.0435.4435.4631.1518.873.593.290.17
RECITEModel=Llama-3.1-70B-Instruct, Knowledge Restriction=Parameter knowledge only2025.041.95—80.1878.733.823.090.23
RECITEModel=Llama-3.1-8B-Instruct, Knowledge Restriction=Parameter knowledge only2025.040.95—56.5148.493.052.040.23