Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Conversational response generation on TopiOCQA
Loading...
30.6
F1 Score
ChatR1-7b
5.744
12.197
18.65
25.103
Oct 15, 2025
F1 Score
BERTScore
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
BERTScore
ChatR1-7b
RAG=RAG, LLM=Qwen-7b,...
2025.10
30.6
79.5
UniConv
RAG=RAG, LLM=Mistral 7...
2025.10
29.6
-
ChatR1-3b
RAG=RAG, LLM=Qwen-3b,...
2025.10
29.4
80.9
ChatRetriever +Mis.
RAG=RAG, LLM=Mistral 7...
2025.10
28.3
-
Claude (DI)
RAG=No, LLM=Claude, Tr...
2025.10
27.2
-
conv-ANCE +Mis.
RAG=RAG, LLM=Mistral 7...
2025.10
27.2
-
ChatGPT (DI)
RAG=No, LLM=GPT-3.5, T...
2025.10
25.5
77.5
ChatR1 (w/o Rint.)
RAG=RAG, LLM=Qwen-3b,...
2025.10
24.4
73
QR Search R1
RAG=RAG, LLM=Qwen-3b,...
2025.10
20.1
72.7
SFT
RAG=No, LLM=Qwen-3b, T...
2025.10
18
78.8
CoT R1
RAG=No, LLM=Qwen-3b, T...
2025.10
12.5
70.3
IRCoT
RAG=RAG, LLM=Qwen-3b,...
2025.10
8.9
61
Qwen-Instr. (RAG)
RAG=RAG, LLM=Qwen-3b,...
2025.10
8.8
54.7
Qwen-Instr. (DI)
RAG=No, LLM=Qwen-3b, T...
2025.10
6.7
57.3
Qwen-Instr. (CoT)
RAG=No, LLM=Qwen-3b, T...
2025.10
6.7
58.6
Feedback
Search any
task
Search any
task