List your company

Short-form generation on TriviaQA

0.87AUROCSeSE
0.65160.70830.7650.8217Nov 20, 2025

Evaluation results

MethodLinks
SeSEModel=Qwen-2-7B2025.110.870.78
SCModel=Qwen-2-72B2025.110.860.87
SGDModel=Qwen-2-7B2025.110.850.76
KLEModel=Qwen-2-7B2025.110.850.75
P(True)Model=Qwen-2-72B2025.110.840.87
P(True)Model=Qwen-2-7B2025.110.830.74
SeSEModel=Llama-3.1-70B2025.110.820.91
SEModel=Qwen-2-7B2025.110.820.73
SCModel=Llama-3.1-70B2025.110.810.91
KLEModel=Llama-3.1-70B2025.110.810.91
SeSEModel=Qwen-2-72B2025.110.790.87
SeSEModel=Llama-3.1-8B2025.110.780.73
SGDModel=Llama-3.1-70B2025.110.780.91
SCModel=Qwen-2-7B2025.110.780.72
LN-PEModel=Qwen-2-7B2025.110.780.78
KLEModel=Qwen-2-72B2025.110.780.84
P(True)Model=Llama-3.1-70B2025.110.770.9
P(True)Model=Llama-3.1-8B2025.110.760.72
KLEModel=Llama-3.1-8B2025.110.760.71
SEModel=Llama-3.1-70B2025.110.760.9
ERModel=Qwen-2-7B2025.110.760.78
SGDModel=Qwen-2-72B2025.110.760.83
LN-PEModel=Llama-3.1-70B2025.110.740.9
ERModel=Qwen-2-72B2025.110.730.83
SEModel=Qwen-2-72B2025.110.730.82
SCModel=Llama-3.1-8B2025.110.720.68
ERModel=Llama-3.1-8B2025.110.710.66
SGDModel=Llama-3.1-8B2025.110.680.66
LN-PEModel=Qwen-2-72B2025.110.680.81
LN-PEModel=Llama-3.1-8B2025.110.660.66
SEModel=Llama-3.1-8B2025.110.660.64
ERModel=Llama-3.1-70B2025.110.660.88