List your company

Dialogue Planning on P4G (test)

3.12Average Turn (AT)UP-NRPA
2.884.56.127.74Apr 7, 2026

Evaluation results

MethodLinks
UP-NRPABackbone=Qwen2.5 14B, level=22026.043.1298.49
DialogXpertBackbone=Qwen2.5 14B2026.043.3491.29
UP-NRPABackbone=Qwen2.5 14B, level=12026.043.491.84
DialogXpertBackbone=Qwen1-1.8B2026.043.9787.93
UP-NRPABackbone=GPT-4o mini, level=22026.044.36100
UP-NRPABackbone=GPT-4o mini, level=12026.044.9197.47
DialogXpertBackbone=Vicuna 13B2026.045.0781.32
LDPPBackbone=Qwen1-1.8B2026.045.5779.5
LDPP w/o 2nd StageBackbone=Qwen1-1.8B2026.046.1476
LDPP w/o 3rd StageBackbone=Qwen1-1.8B2026.046.8457
UDPBackbone=GPT-4o mini2026.047.70559.8
ProCoT2026.047.9854.3
UDP w/o RLBackbone=GPT-4o mini2026.04853.3
UDP w/o PTBackbone=GPT-4o mini2026.048.01751.3
ICL-AIF2026.048.0646.5
PPDPPBackbone=Vicuna 13B2026.048.18546.3
TRIPBackbone=GPT3.52026.048.249.5
Standard2026.048.3246.8
GDP-Zero2026.049.1232.8