Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Target-guided Proactive Dialogue Generation on DuRecDial OOD (test)
Loading...
4.17
Perplexity
TRIPDial
4.1224
4.4437
4.765
5.0863
May 12, 2026
Perplexity
F1 (Word)
BLEU-1
BLEU-2
DIST-1
DIST-2
F1 (K)
Failure Rate
Updated 21d ago
Evaluation Results
Method
Method
Links
Perplexity
F1 (Word)
BLEU-1
BLEU-2
DIST-1
DIST-2
F1 (K)
Failure Rate
TRIPDial
repro=⋄
2026.05
4.17
42.68
41.1
33.5
1.3
5.9
47.13
22.19
TPDial
repro=⋄
2026.05
4.18
34.95
34.8
27.1
1.3
5.8
34.8
80.05
T5-Zh
2026.05
4.56
40.7
39.4
31.2
1.2
5.9
41.42
23.44
Our
mode=soft
2026.05
5.34
44.33
43.2
34.8
1.2
6.5
47.83
20.2
Our
mode=hard
2026.05
5.36
44.2
43.1
34.7
1.2
6.6
47.83
19.7
Feedback
Search any
task
Search any
task