List your company

Multi-turn information acquisition on Beauty

82.9Success RateCUP
8.269627.644847.0266.3952Apr 5, 2026

Evaluation results

MethodLinks
CUPModel=Mistral-7B-v0.32026.0482.94.06
CUPModel=Qwen3-4B2026.0482.124.1
CUPModel=Llama-3.1-8B2026.0481.994.06
MISQ-HFModel=Llama-3.1-8B2026.0469.954.31
BED-LLMModel=Llama-3.1-8B2026.0468.784.38
MISQ-HFModel=Mistral-7B-v0.32026.0464.94.3
MISQ-HFModel=Qwen3-4B2026.0463.214.33
BED-LLMModel=Mistral-7B-v0.32026.0461.534.62
UoTModel=Llama-3.1-8B2026.0457.94.69
BED-LLMModel=Qwen3-4B2026.0455.574.49
UoTModel=Mistral-7B-v0.32026.0453.114.73
UoTModel=Qwen3-4B2026.0451.684.67
ATDModel=Mistral-7B-v0.32026.0449.224.69
ATDModel=Llama-3.1-8B2026.0449.094.66
ATDModel=Qwen3-4B2026.0448.964.7
LLM-planningModel=Llama-3.1-8B2026.0444.434.75
LLM-planningModel=Qwen3-4B2026.0444.34.72
LLM-planningModel=Mistral-7B-v0.32026.0443.014.81
CoTModel=Qwen3-4B2026.0438.474.11
CoTModel=Llama-3.1-8B2026.0437.824.1
Direct PromptingModel=Qwen3-4B2026.0437.054.18
CoTModel=Mistral-7B-v0.32026.0435.424.17
Direct PromptingModel=Llama-3.1-8B2026.0433.944.22
Direct PromptingModel=Mistral-7B-v0.32026.0432.254.2
SBERT2026.0411.144.82