List your company

Knowledge-grounded Dialogue on Wizard of Wikipedia (WoW)

78.6Performance Scoreo1
55.30461.35267.473.448Apr 9, 2026

Evaluation results

MethodLinks
o12026.0478.6
GuarantRAGBase Model=Qwen3-14B, Thinking Mode=false2026.0477.8
GPT-4o2026.0477.2
GuarantRAGBase Model=Qwen3-14B, Thinking Mode=true2026.0476.2
GuarantRAGBase Model=Qwen3-8B, Thinking Mode=false2026.0475.1
P-RAGBase Model=Qwen3-14B, Thinking Mode=false2026.0474.3
P-RAGBase Model=Qwen3-14B, Thinking Mode=true2026.0473.8
SOLARBase Model=Qwen3-14B, Thinking Mode=false2026.0472.4
SOLARBase Model=Qwen3-14B, Thinking Mode=true2026.0472.1
DRAGINBase Model=Qwen3-14B, Thinking Mode=false2026.0472
DRAGINBase Model=Qwen3-14B, Thinking Mode=true2026.0471.6
FLAREBase Model=Qwen3-14B, Thinking Mode=false2026.0471.5
P-RAGBase Model=Qwen3-8B, Thinking Mode=false2026.0471.2
FLAREBase Model=Qwen3-14B, Thinking Mode=true2026.0471.2
RQ-RAGBase Model=Qwen3-14B, Thinking Mode=false2026.0470.9
RQ-RAGBase Model=Qwen3-14B, Thinking Mode=true2026.0470.4
SOLARBase Model=Qwen3-8B, Thinking Mode=false2026.0469.5
SelfRAGBase Model=Qwen3-14B, Thinking Mode=false2026.0469.3
DRAGINBase Model=Qwen3-8B, Thinking Mode=false2026.0469.1
SelfRAGBase Model=Qwen3-14B, Thinking Mode=true2026.0468.9
FLAREBase Model=Qwen3-8B, Thinking Mode=false2026.0468.7
DA-RAGBase Model=Qwen3-14B, Thinking Mode=false2026.0468.2
RQ-RAGBase Model=Qwen3-8B, Thinking Mode=false2026.0468.1
DA-RAGBase Model=Qwen3-14B, Thinking Mode=true2026.0467.8
SelfRAGBase Model=Qwen3-8B, Thinking Mode=false2026.0466.8
DA-RAGBase Model=Qwen3-8B, Thinking Mode=false2026.0465.4
Standard RAGBase Model=Qwen3-14B, Thinking Mode=false2026.0465.1
Standard RAGBase Model=Qwen3-14B, Thinking Mode=true2026.0464.7
Standard RAGBase Model=Qwen3-8B, Thinking Mode=false2026.0462.7
Qwen3-14B-TBase Model=Qwen3-14B, Thinking Mode=true2026.0459.3
Qwen3-14BBase Model=Qwen3-14B, Thinking Mode=false2026.0458.7
Qwen3-8BBase Model=Qwen3-8B, Thinking Mode=false2026.0456.2