List your company

Question Answering on NaturalQA

38.92EMDTR
16.539222.349628.1633.9704Jan 7, 2026

Evaluation results

MethodLinks
DTRGenerator=Qwen2.5-72B-Instruct, Threshold u=0.0012026.0138.9251.2888.1
DTRGenerator=Qwen2.5-7B-Instruct, Retriever=e5, Top-k retrievals=3, Uncertainty threshold (u)=0.0012026.0138.8449.2294.8
DTRGenerator=Qwen2.5-7B-Instruct, Retriever=bge, Retrieval depth (top-k)=5, Uncertainty threshold (u)=0.0012026.0138.548.6394.8
DTRGenerator=Qwen2.5-7B-Instruct, Retriever=e5, Top-k retrievals=3, Uncertainty threshold (u)=0.0052026.0138.1248.6490.4
DTRGenerator=Qwen2.5-7B-Instruct, Threshold u=0.0012026.0138.0347.8394.8
DTRGenerator=Qwen2.5-7B-Instruct, Retriever=bge, Retrieval depth (top-k)=5, Uncertainty threshold (u)=0.0052026.0137.9548.1390.4
DTRGenerator=Qwen2.5-7B-Instruct, Retriever=e5, Top-k retrievals=3, Uncertainty threshold (u)=0.012026.0137.9248.4587.5
DTRGenerator=Qwen2.5-7B-Instruct, Retriever=bge, Retrieval depth (top-k)=5, Uncertainty threshold (u)=0.012026.0137.6747.9587.5
Standard RAGGenerator=Qwen2.5-7B-Instruct, Retriever=e5, Top-k retrievals=32026.0137.5647.29—
CoTGenerator=Qwen2.5-7B-Instruct, Retriever=bge, Retrieval depth (top-k)=52026.0137.1747.46—
Q2DGenerator=Qwen2.5-7B-Instruct, Retriever=bge, Retrieval depth (top-k)=52026.0136.8747.15—
HyDEGenerator=Qwen2.5-7B-Instruct, Retriever=bge, Retrieval depth (top-k)=52026.0136.746.35—
Standard RAGGenerator=Qwen2.5-7B-Instruct, Retriever=bge, Retrieval depth (top-k)=52026.0136.4546.23—
CoTGenerator=Qwen2.5-7B-Instruct, Retriever=e5, Top-k retrievals=32026.0136.1845.89—
Q2DGenerator=Qwen2.5-7B-Instruct, Retriever=e5, Top-k retrievals=32026.0135.9345.87—
HyDEGenerator=Qwen2.5-7B-Instruct, Retriever=e5, Top-k retrievals=32026.0135.3244.92—
Standard RAGGenerator=Qwen2.5-7B-Instruct, Retriever=bge-large-en-v1.5, top-k=32026.0134.2944—
LLM JudgeGenerator=Qwen2.5-7B-Instruct, Retriever=e5, Top-k retrievals=3, Judge Model=72B2026.0128.5337.6643.7
LLM Judge (72B)Generator=Qwen2.5-7B-Instruct, Retriever=bge, Retrieval depth (top-k)=52026.0127.8936.7843.7
LLM Judge (72B)Generator=Qwen2.5-7B-Instruct, Retriever=bge-large-en-v1.52026.0126.7935.6443.7
No RetrievalGenerator=Qwen2.5-7B-Instruct, Retriever=None, Top-k retrievals=02026.0117.424.95—
LLM JudgeGenerator=Qwen2.5-7B-Instruct, Retriever=e5, Top-k retrievals=3, Judge Model=7B2026.0117.424.950
No RetrievalGenerator=Qwen2.5-7B-Instruct, Retriever=None2026.0117.424.95—
LLM Judge (7B)Generator=Qwen2.5-7B-Instruct, Retriever=bge-large-en-v1.52026.0117.424.950
No RetrievalGenerator=Qwen2.5-7B-Instruct, Retriever=None2026.0117.424.95—
LLM Judge (7B)Generator=Qwen2.5-7B-Instruct, Retriever=bge, Retrieval depth (top-k)=52026.0117.424.950