Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
POI Attribute Acquisition (Task-oriented Dialogue) on DuIVRS logs Dgeneral 1.0 (test)
Loading...
73.83
Completion Rate
HybridLLMs
43.2332
51.1766
59.12
67.0634
May 18, 2026
Completion Rate
Updated 2mo ago
Evaluation Results
Method
Method
Links
Completion Rate
HybridLLMs
LLM-S=Qwen2.5-1.5B, LL...
2026.05
73.83
DuIVRS-2
LLM-S=ERNIE-Bot-tiny,...
2026.05
73.7
LLM-DM
2026.05
67.4
GPT-4o
2026.05
64.81
DeepSeek-V3
2026.05
63.87
DuIVRS-1
2026.05
62.99
w/o-DA
2026.05
62.36
Direct-SFT
2026.05
60.33
w/o-CoT
2026.05
44.41
Feedback
Search any
task
Search any
task