Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Knowledge-grounded Dialogue Generation on OpenDialKG
Loading...
81.67
Faithfulness
RHO
72.31
74.74
77.17
79.6
Dec 3, 2022
Faithfulness
Intrinsic Hallucination
Extrinsic Hallucination
Both Hallucination
Updated 1mo ago
Evaluation Results
Method
Method
Links
Faithfulness
Intrinsic Hallucination
Extrinsic Hallucination
Both Hallucination
RHO
Response Re-ranking=tr...
2022.12
81.67
7.67
10
0.67
RHO w/o RR
Response Re-ranking=fa...
2022.12
80.67
7.67
10.67
1
BART+NPH
Backbone=BART, Framewo...
2022.12
75
9.33
15.33
0.33
GPT2+NPH
Backbone=GPT2, Framewo...
2022.12
72.67
8.67
18
0.67
Feedback
Search any
task
Search any
task