Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Document-grounded Dialogue on MultiDoc2Dial
Loading...
66.1
EM
PoP
57.052
59.401
61.75
64.099
Feb 27, 2026
EM
Hallucination Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
EM
Hallucination Rate
PoP
Reasoning protocol=PoP
2026.02
66.1
10.2
ProgVLM
Reasoning protocol=Pro...
2026.02
63.4
14.1
MM-ReAct
Reasoning protocol=MM-...
2026.02
62.8
14.5
M-CoT
Reasoning protocol=M-CoT
2026.02
60
18.2
Direct
Reasoning protocol=Direct
2026.02
57.4
20.4
Feedback
Search any
task
Search any
task
