Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Conversational response generation on FaithDial
Loading...
19.2
F1 Score
ChatR1-3b
9.216
11.808
14.4
16.992
Oct 15, 2025
F1 Score
BERTScore
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
BERTScore
ChatR1-3b
RAG=RAG, LLM=Qwen-3b,...
2025.10
19.2
84
SFT
RAG=No, LLM=Qwen-3b, T...
2025.10
18.6
83.8
ChatR1-7b
RAG=RAG, LLM=Qwen-7b,...
2025.10
18.1
84.8
ChatR1 (w/o Rint.)
RAG=RAG, LLM=Qwen-3b,...
2025.10
15.5
81.3
CoT R1
RAG=No, LLM=Qwen-3b, T...
2025.10
14.5
80.9
QR Search R1
RAG=RAG, LLM=Qwen-3b,...
2025.10
14.4
82.2
ChatGPT (DI)
RAG=No, LLM=GPT-3.5, T...
2025.10
12.9
80.9
Qwen-Instr. (RAG)
RAG=RAG, LLM=Qwen-3b,...
2025.10
12.3
73.8
UniConv
RAG=RAG, LLM=Mistral 7...
2025.10
11.6
-
Qwen-Instr. (DI)
RAG=No, LLM=Qwen-3b, T...
2025.10
10.9
64.8
Qwen-Instr. (CoT)
RAG=No, LLM=Qwen-3b, T...
2025.10
9.6
64.8
IRCoT
RAG=RAG, LLM=Qwen-3b,...
2025.10
9.6
64.7
Feedback
Search any
task
Search any
task