List your company

Dialogue Planning on CraigslistBargain

2.32ATDialogXpert
2.14363.33434.5255.7157Apr 7, 2026

Evaluation results

MethodLinks
DialogXpertBackbone=Qwen2.5 14B2026.042.3297.460.4389
NRPA-GD level 2Backbone=GPT-4o mini2026.042.721000.6422
DialogXpert -w/o EmotionBackbone=Qwen2.5 14B2026.042.7591.360.3156
DPDP -System 2Backbone=GPT-3.5-Turbo2026.042.7897.340.2728
DialogXpertBackbone=Qwen 1.8B2026.042.7892.740.3791
UP-NRPA level 2Backbone=Qwen2.5 14B2026.042.881000.6865
DialogXpertBackbone=Vicuna 13B2026.042.9394.150.3811
UP-NRPA level 1Backbone=Qwen2.5 14B2026.043.141000.5835
DialogXpert -w/o LLM-PriorBackbone=Qwen2.5 14B2026.043.3191.650.3598
DialogXpert -w/o RLBackbone=Qwen2.5 14B2026.043.6487.540.2952
NRPA-GD level 1Backbone=GPT-4o mini2026.043.8998.940.6326
DialogXpert -w/o RLBackbone=Qwen 1.8B2026.044.6977.540.3012
UP-NRPA level 2Backbone=GPT-4o mini2026.044.7497.870.9069
DPDP (System 1)Backbone=GPT-3.5-Turbo2026.045.0374.470.4108
DialogXpert -w/o RLBackbone=Vicuna 13B2026.045.1375.610.3473
UP-NRPA level 1Backbone=GPT-4o mini2026.045.2290.960.7882
PPDPP -w/o RLBackbone=Vicuna 13B2026.045.5766.490.228
PPDPPBackbone=Vicuna 13B2026.045.6261.170.3376
PPDPP -w/o SFTBackbone=Vicuna 13B2026.045.7162.230.3354
Proactive + MI-PromptBackbone=-2026.045.7456.910.268
ProactiveBackbone=-2026.045.856.380.2489
AnEBackbone=-2026.045.9145.210.2608
ProCoT + MI-PromptBackbone=-2026.046.1255.320.3059
ProCoTBackbone=-2026.046.2253.190.2486
StandardBackbone=-2026.046.4738.30.1588
ICL-AIFBackbone=-2026.046.5336.170.1881
DialoGPTBackbone=GPT-22026.046.7332.450.2012