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

Proactive Dialogue Evaluation on DuRecDial OOD 2.0 (test)

4.07Proactivity

Qwen 32B

Updated 21d ago

Evaluation Results

Method	Links
Qwen 32B 2026.05		4.07	4.91	4.86	4.13
Qwen 14B 2026.05		4.02	4.92	4.83	3.83
LLaMA 8B 2026.05		3.78	4.82	4.69	4.03
Ours 0.3B 2026.05		2.71	4.33	3.98	1.98
Qwen 3B 2026.05		2.35	4.29	4.09	1.88
LLaMA 3B 2026.05		2.32	4.29	4.07	1.89
LLaMA 1B 2026.05		2.31	4.33	3.97	1.89