List your company

Question Answering on Sports understanding

68.4AccuracyCoT-decoding
47.18452.69258.263.708Apr 8, 2026

Evaluation results

MethodLinks
CoT-decodingModel=Gemma-7B, Spec Ans=Yes2026.0468.4
GCoT-decoding + SpanAlignModel=Gemma-7B, Spec Ans=No2026.0467.2
GCoT-decodingModel=Gemma-7B, Spec Ans=No2026.0465.2
Self-consistencyModel=Gemma-7B, Spec Ans=Yes2026.0463.9
GreedyModel=Gemma-7B, Spec Ans=No2026.0461.2
Temperature samplingModel=Gemma-7B, Spec Ans=No2026.0460.1
Beam searchModel=Gemma-7B, Spec Ans=No2026.0459.9
Top-k samplingModel=Gemma-7B, Spec Ans=No2026.0458
GCoT-decodingModel=Llama-3.1-8B, Spec Ans=No2026.0458
Self-consistencyModel=Llama-3.1-8B, Spec Ans=Yes2026.0454.6
Self-consistencyModel=Mistral-7B, Spec Ans=Yes2026.0452.9
Temperature samplingModel=Llama-3.1-8B, Spec Ans=No2026.0452.4
GCoT-decoding + SpanAlignModel=Llama-3.1-8B, Spec Ans=No2026.0452
GCoT-decodingModel=Mistral-7B, Spec Ans=No2026.0452
Top-k samplingModel=Llama-3.1-8B, Spec Ans=No2026.0451.9
GreedyModel=Llama-3.1-8B, Spec Ans=No2026.0451.6
CoT-decodingModel=Llama-3.1-8B, Spec Ans=Yes2026.0451
Beam searchModel=Llama-3.1-8B, Spec Ans=No2026.0450.7
CoT-decodingModel=Mistral-7B, Spec Ans=Yes2026.0450.6
Top-k samplingModel=Mistral-7B, Spec Ans=No2026.0450.3
GreedyModel=Mistral-7B, Spec Ans=No2026.0449.6
Temperature samplingModel=Mistral-7B, Spec Ans=No2026.0448.9
Beam searchModel=Mistral-7B, Spec Ans=No2026.0448.2
GCoT-decoding + SpanAlignModel=Mistral-7B, Spec Ans=No2026.0448