List your company

POI Attribute Acquisition (Task-oriented Dialogue) on DuIVRS logs Drobust 1.0 (test)

76.22Completion Rate (CR)DuIVRS-2
26.435239.360152.28565.2099May 18, 2026

Evaluation results

MethodLinks
DuIVRS-2LLM-S=ERNIE-Bot-tiny, LLM-L=ERNIE-Bot-turbo, Black-box LLM=ERNIE 4.02026.0576.22
HybridLLMsLLM-S=Qwen2.5-1.5B, LLM-L=Qwen2.5-7B, Black-box LLM=GPT-4o2026.0575.89
DuIVRS-12026.0569.05
DeepSeek-V32026.0564.55
GPT-4o2026.0563.13
LLM-DM2026.0560.98
w/o-DA2026.0554.12
Direct-SFT2026.0552.9
w/o-CoT2026.0528.35