List your company

Dialogue Generation on DuRecDial OOD 2.0 (test)

3.03ProactivityOurs
2.16682.39092.6152.8391May 12, 2026

Evaluation results

MethodLinks
OursEvaluation Protocol=LLM-as-a-judge2026.053.034.534.282.58
T5-FlanEvaluation Protocol=LLM-as-a-judge2026.052.64.253.772.1
TRIPDialEvaluation Protocol=LLM-as-a-judge2026.052.243.953.632.15
TPDialEvaluation Protocol=LLM-as-a-judge2026.052.23.953.431.73