Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Conversational Recommendation on Yelp (test)
Loading...
57
Success Rate
ReAct
20.6
30.05
39.5
48.95
Jun 17, 2025
Success Rate
Recall
Wrong Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
Recall
Wrong Rate
ReAct
Backbone=GPT-4o mini,...
2025.06
57
62
42
ActCRS+ECPO
Backbone=Llama-3.1-8B-...
2025.06
45
47
63
ActCRS+SGPT
Backbone=Llama-3.1-8B-...
2025.06
44
48
47
MACRS
Backbone=GPT-4o mini,...
2025.06
40
41
2
ActCRS
Backbone=GPT-4o mini,...
2025.06
37
43
50
ReAct
Backbone=Llama-3.1-8B-...
2025.06
31
40
16
ChatRec
Backbone=Llama-3.1-8B-...
2025.06
30
32
5
ChatRec
Backbone=GPT-4o mini,...
2025.06
24
30
12
MACRS
Backbone=Llama-3.1-8B-...
2025.06
22
24
1
ActCRS
Backbone=Llama-3.1-8B-...
2025.06
22
35
38
Feedback
Search any
task
Search any
task