List your company

Dialogue Planning on ExTES (test)

8.163Average Turn (AT)PPDPP
2.346283.856395.36656.87661Apr 7, 2026

Evaluation results

MethodLinks
PPDPPBackbone=Vicuna 13B2026.048.16355.8
ICL-AIF2026.047.6555.5
LDPP w/o 3rd StageBackbone=Qwen1-1.8B2026.047.03862.3
UP-NRPABackbone=GPT-4o mini, level=12026.044.7199
LDPP w/o 2nd StageBackbone=Qwen1-1.8B2026.044.48386.5
UP-NRPABackbone=GPT-4o mini, level=22026.044.22100
LDPPBackbone=Qwen1-1.8B2026.044.13290.3
UP-NRPABackbone=Qwen2.5 14B, level=12026.043.29100
DialogXpertBackbone=Vicuna 13B2026.042.9795.34
DialogXpertBackbone=Qwen1-1.8B2026.042.7396.51
UP-NRPABackbone=Qwen2.5 14B, level=22026.042.69100
DialogXpertBackbone=Qwen2.5 14B2026.042.5797.82