List your company
ResearchFormerly WizWand

Conversational Response Generation on QReCC

31F1 ScoreChatR1-7b
12.07216.98621.926.814Oct 15, 2025
Updated 6mo ago

Evaluation results

MethodLinks
ChatR1-7bRAG=RAG, LLM=Qwen-7b, Training Strategy=Supervised Fine-tuning or RL Training2025.103180.7
ChatR1-3bRAG=RAG, LLM=Qwen-3b, Training Strategy=Supervised Fine-tuning or RL Training2025.102879.2
ChatR1 (w/o Rint.)RAG=RAG, LLM=Qwen-3b, Training Strategy=Supervised Fine-tuning or RL Training2025.102778.5
ChatRetriever +Mis.RAG=RAG, LLM=Mistral 7b, Training Strategy=Supervised Fine-tuning or RL Training2025.1026.3—
UniConvRAG=RAG, LLM=Mistral 7b, Training Strategy=Supervised Fine-tuning or RL Training2025.1026.2—
conv-ANCE +Mis.RAG=RAG, LLM=Mistral 7b, Training Strategy=Supervised Fine-tuning or RL Training2025.1025.9—
Claude (DI)RAG=No, LLM=Claude, Training Strategy=Zero-Shot2025.1025—
SFTRAG=No, LLM=Qwen-3b, Training Strategy=Supervised Fine-tuning or RL Training2025.1023.380
ChatGPT (DI)RAG=No, LLM=GPT-3.5, Training Strategy=Zero-Shot2025.1022.675.6
QR Search R1RAG=RAG, LLM=Qwen-3b, Training Strategy=Supervised Fine-tuning or RL Training2025.1020.479.6
CoT R1RAG=No, LLM=Qwen-3b, Training Strategy=Supervised Fine-tuning or RL Training2025.1017.772.6
Qwen-Instr. (RAG)RAG=RAG, LLM=Qwen-3b, Training Strategy=Zero-Shot2025.1015.564.5
Qwen-Instr. (DI)RAG=No, LLM=Qwen-3b, Training Strategy=Zero-Shot2025.1013.355.3
IRCoTRAG=RAG, LLM=Qwen-3b, Training Strategy=Zero-Shot2025.1013.155.6
Qwen-Instr. (CoT)RAG=No, LLM=Qwen-3b, Training Strategy=Zero-Shot2025.1012.858.5