Share your thoughts, 1 month free Claude Pro on usSee more

Open-ended Dialogue Generation on CMD (test)

19.4Rouge-L

NSR

Updated 6d ago

Evaluation Results

Method	Links
NSR 2026.05		19.4	79.2	22	87.9	52.1
W-REINFORCE 2026.05		19.4	77.8	22	87.4	51.7
NSR 2026.05		19.4	79.2	22	87.9	52.1
W-REINFORCE 2026.05		19.4	77.8	22	87.4	51.7
W-REINFORCE 2026.05		18.7	79.3	21	86.2	51.3
EAPO 2026.05		18.7	79.8	21.3	86.4	51.6
W-REINFORCE 2026.05		18.7	79.3	21	86.2	51.3
EAPO 2026.05		18.7	79.8	21.3	86.4	51.6
GRPO 2026.05		18.6	78.3	20.6	83.8	50.3
W-REINFORCE 2026.05		18.6	75.4	21.6	87.6	50.8
GRPO 2026.05		18.6	78.3	20.6	83.8	50.3
W-REINFORCE 2026.05		18.6	75.4	21.6	87.6	50.8
W-REINFORCE 2026.05		18.5	80.8	20.7	87.1	51.8
W-REINFORCE 2026.05		18.5	80.8	20.7	87.1	51.8
W-REINFORCE 2026.05		18.4	78.7	20.7	85.2	50.8
W-REINFORCE 2026.05		18.4	78.7	20.7	85.2	50.8
W-REINFORCE 2026.05		17.3	75.2	19.9	83.8	49
W-REINFORCE 2026.05		17.3	75.2	19.9	83.8	49
W-REINFORCE 2026.05		17	76.3	19.5	85.2	49.5
W-REINFORCE 2026.05		17	76.3	19.5	85.2	49.5
W-REINFORCE 2026.05		16	74.9	18.4	82.7	48
W-REINFORCE 2026.05		16	74.9	18.4	82.7	48
W-REINFORCE 2026.05		15.8	72.4	18.3	80.6	46.7
W-REINFORCE 2026.05		15.8	72.4	18.3	80.6	46.7
PSR 2026.05		14.7	68.8	17.3	82.1	45.7
PSR 2026.05		14.7	68.8	17.3	82.1	45.7