List your company

Multiple Choice Question Answering on ConFiQA MC

91.2F1 ScoreProbeRAG
0.92824.36447.871.236Oct 14, 2025

Evaluation results

MethodLinks
ProbeRAGCategory=Training-Based, Backbone=Mistral-7B-v0.32025.1091.289.7
ProbeRAGCategory=Training-Based, Backbone=Qwen3-8B2025.1090.789.7
ProbeRAGCategory=Training-Based, Backbone=LLaMA-3.1-8B-Instruct2025.1089.287.7
ProbeRAGArchitecture=Qwen2.5-7B-Instruct2025.1088.886.2
CANOECategory=Training-Based, Backbone=Mistral-7B-v0.32025.1087.285.7
ParamMuteCategory=Training-Based, Backbone=Qwen3-8B2025.1086.380.2
ParamMuteCategory=Training-Based, Backbone=Mistral-7B-v0.32025.1086.382.1
CANOECategory=Training-Based, Backbone=Qwen3-8B2025.1085.281.7
CANOECategory=Training-Based, Backbone=LLaMA-3.1-8B-Instruct2025.1080.974.2
ProbeRAGArchitecture=LLaMA-2-7B-Chat-HF2025.1079.169.7
Context-DPOCategory=Training-Based, Backbone=LLaMA-3.1-8B-Instruct2025.1076.967.7
CANOEArchitecture=LLaMA-2-7B-Chat-HF2025.1073.970.2
FaithfulRAGCategory=Prompt-Based, Backbone=Qwen3-8B2025.1072.360.1
Opin(Instr)Category=Prompt-Based, Backbone=Qwen3-8B2025.1070.761.1
ParamMuteCategory=Training-Based, Backbone=LLaMA-3.1-8B-Instruct2025.1070.660.9
FaithfulRAGCategory=Prompt-Based, Backbone=LLaMA-3.1-8B-Instruct2025.1070.361.2
CANOEArchitecture=Qwen2.5-7B-Instruct2025.1068.761.1
KRECategory=Prompt-Based, Backbone=LLaMA-3.1-8B-Instruct2025.1068.259.8
KRECategory=Prompt-Based, Backbone=Qwen3-8B2025.1067.559.1
Opin(Instr)Category=Prompt-Based, Backbone=LLaMA-3.1-8B-Instruct2025.1067.457.3
COIECDCategory=Decoding-Based, Backbone=Qwen3-8B2025.1066.760.8
AdaCADCategory=Decoding-Based, Backbone=Qwen3-8B2025.1064.258.7
Context-DPOArchitecture=Qwen2.5-7B-Instruct2025.1062.753.7
FaithfulRAGCategory=Prompt-Based, Backbone=Mistral-7B-v0.32025.1060.344.3
Full-ContextCategory=Baseline, Backbone=Qwen3-8B2025.1059.650.2
Context-DPOCategory=Training-Based, Backbone=Qwen3-8B2025.1059.650.1
Opin(Instr)Category=Prompt-Based, Backbone=Mistral-7B-v0.32025.1058.844.1
KRECategory=Prompt-Based, Backbone=Mistral-7B-v0.32025.1058.745
Context-DPOArchitecture=LLaMA-2-7B-Chat-HF2025.1057.932
CADCategory=Decoding-Based, Backbone=Qwen3-8B2025.1057.748.3
Context-DPOCategory=Training-Based, Backbone=Mistral-7B-v0.32025.1044.828.3
AdaCADCategory=Decoding-Based, Backbone=LLaMA-3.1-8B-Instruct2025.1043.332.5
AdaCADCategory=Decoding-Based, Backbone=Mistral-7B-v0.32025.1033.723.4
COIECDCategory=Decoding-Based, Backbone=LLaMA-3.1-8B-Instruct2025.1028.524
Full-ContextCategory=Baseline, Backbone=LLaMA-3.1-8B-Instruct2025.102822.5
COIECDCategory=Decoding-Based, Backbone=Mistral-7B-v0.32025.1026.114.5
Full-ContextCategory=Baseline, Backbone=Mistral-7B-v0.32025.1025.612.5
CADCategory=Decoding-Based, Backbone=Mistral-7B-v0.32025.1016.75.9
CADCategory=Decoding-Based, Backbone=LLaMA-3.1-8B-Instruct2025.101611.4
No-ContextCategory=Baseline, Backbone=Qwen3-8B2025.107.63.6
No-ContextCategory=Baseline, Backbone=LLaMA-3.1-8B-Instruct2025.1052.1
No-ContextCategory=Baseline, Backbone=Mistral-7B-v0.32025.104.40.9