List your company
ResearchFormerly WizWand

Question Answering on MuSiQue (Accuracy (ACC))

79.9Accuracy (ACC)FaithfulRAG
4.70824.22943.7563.271Mar 2, 2025Mar 18, 2025Apr 4, 2025Apr 21, 2025May 7, 2025May 24, 2025Jun 10, 2025
Updated 8mo ago

Evaluation results

MethodLinks
FaithfulRAGBackbone LLM=llama3.1-8b-instruct2025.0679.9
ATTRBackbone LLM=qwen2.5-7b-instruct2025.0678.7
CADBackbone LLM=qwen2.5-7b-instruct2025.0678.6
FaithfulRAGBackbone LLM=mistral-7b-instruct2025.0678.5
FaithfulRAGBackbone LLM=qwen2.5-7b-instruct2025.0678
ChatQA-2.0Backbone LLM=Llama3.1-8B2025.0677.2
Opin(Instr)Backbone LLM=qwen2.5-7b-instruct2025.0676.9
Origin model with full contextBackbone LLM=qwen2.5-7b-instruct2025.0675.2
ChatQA-1.5Backbone LLM=Llama3.1-8B2025.0675
CADBackbone LLM=llama3.1-8b-instruct2025.0672.6
KREBackbone LLM=qwen2.5-7b-instruct2025.0670.7
COIECDBackbone LLM=llama3.1-8b-instruct2025.0670.5
Opin(Instr)Backbone LLM=llama3.1-8b-instruct2025.0670.3
COIECDBackbone LLM=qwen2.5-7b-instruct2025.0669.7
Opin(Instr)Backbone LLM=mistral-7b-instruct2025.0668.1
Origin model with full contextBackbone LLM=llama3.1-8b-instruct2025.0667.8
Origin model with full contextBackbone LLM=mistral-7b-instruct2025.0667.6
COIECDBackbone LLM=mistral-7b-instruct2025.0666.8
ATTRBackbone LLM=mistral-7b-instruct2025.0666.1
CADBackbone LLM=mistral-7b-instruct2025.0663.6
ATTRBackbone LLM=llama3.1-8b-instruct2025.0662.8
Self-RAGBackbone LLM=Llama2-7B2025.0654.1
KREBackbone LLM=mistral-7b-instruct2025.0650.6
KREBackbone LLM=llama3.1-8b-instruct2025.0635.9
L-RAGRetrieval Count (K)=82025.0335.2
IRCoT2025.0334.6
VanillaRAGRetrieval Count (K)=42025.0330.5
VanillaRAGRetrieval Count (K)=82025.0329.7
IterRetGen2025.0329.7
L-RAGRetrieval Count (K)=42025.0325.8
Origin model without contextBackbone LLM=qwen2.5-7b-instruct2025.0619.6
SelfAsk2025.0318
Origin model without contextBackbone LLM=mistral-7b-instruct2025.0613.8
Origin model without contextBackbone LLM=llama3.1-8b-instruct2025.0611.2
No RetrievalRetrieval=None2025.039.4
HyDE2025.037.6