List your company

Open-ended Question Answering on ConFiQA (test)

95.7F1 ScoreProbeRAG
2.51626.70850.975.092Oct 14, 2025

Evaluation results

MethodLinks
ProbeRAGCategory=Training-Based, Backbone=Qwen3-8B2025.1095.794.3
ProbeRAGCategory=Training-Based, Backbone=Mistral-7B-v0.32025.1095.193.7
ProbeRAGCategory=Training-Based, Backbone=LLaMA-3.1-8B-Instruct2025.1093.191.7
ParamMuteCategory=Training-Based, Backbone=Mistral-7B-v0.32025.1093.191.2
CANOECategory=Training-Based, Backbone=Mistral-7B-v0.32025.1092.590.7
CANOECategory=Training-Based, Backbone=Qwen3-8B2025.1092.286.5
ParamMuteCategory=Training-Based, Backbone=Qwen3-8B2025.1090.583.7
KRECategory=Prompt-Based, Backbone=Mistral-7B-v0.32025.1084.572.8
KRECategory=Prompt-Based, Backbone=LLaMA-3.1-8B-Instruct2025.108474.7
Context-DPOCategory=Training-Based, Backbone=LLaMA-3.1-8B-Instruct2025.1083.776.7
CANOECategory=Training-Based, Backbone=LLaMA-3.1-8B-Instruct2025.1082.377.7
KRECategory=Prompt-Based, Backbone=Qwen3-8B2025.1080.467.3
Opin(Instr)Category=Prompt-Based, Backbone=Qwen3-8B2025.1078.869.2
COIECDCategory=Decoding-Based, Backbone=Qwen3-8B2025.1078.573.6
ParamMuteCategory=Training-Based, Backbone=LLaMA-3.1-8B-Instruct2025.1078.373.2
Opin(Instr)Category=Prompt-Based, Backbone=LLaMA-3.1-8B-Instruct2025.1076.967.4
AdaCADCategory=Decoding-Based, Backbone=Qwen3-8B2025.1076.968.3
Opin(Instr)Category=Prompt-Based, Backbone=Mistral-7B-v0.32025.1076.465.5
FaithfulRAGCategory=Prompt-Based, Backbone=Qwen3-8B2025.1075.365.3
FaithfulRAGCategory=Prompt-Based, Backbone=Mistral-7B-v0.32025.1074.263.5
Full-ContextCategory=Baseline, Backbone=Qwen3-8B2025.1072.564.2
Context-DPOCategory=Training-Based, Backbone=Qwen3-8B2025.1072.363.9
CADCategory=Decoding-Based, Backbone=Qwen3-8B2025.107162
FaithfulRAGCategory=Prompt-Based, Backbone=LLaMA-3.1-8B-Instruct2025.1070.465.2
COIECDCategory=Decoding-Based, Backbone=LLaMA-3.1-8B-Instruct2025.1067.160.1
Context-DPOCategory=Training-Based, Backbone=Mistral-7B-v0.32025.1066.452.7
COIECDCategory=Decoding-Based, Backbone=Mistral-7B-v0.32025.1058.945.1
Full-ContextCategory=Baseline, Backbone=LLaMA-3.1-8B-Instruct2025.1058.549
Full-ContextCategory=Baseline, Backbone=Mistral-7B-v0.32025.1058.544
AdaCADCategory=Decoding-Based, Backbone=Mistral-7B-v0.32025.1058.246.3
AdaCADCategory=Decoding-Based, Backbone=LLaMA-3.1-8B-Instruct2025.1055.748.1
CADCategory=Decoding-Based, Backbone=Mistral-7B-v0.32025.1053.536.9
CADCategory=Decoding-Based, Backbone=LLaMA-3.1-8B-Instruct2025.1048.338.1
No-ContextCategory=Baseline, Backbone=Qwen3-8B2025.107.81.4
No-ContextCategory=Baseline, Backbone=LLaMA-3.1-8B-Instruct2025.106.11.3
No-ContextCategory=Baseline, Backbone=Mistral-7B-v0.32025.106.11