Answer Generation on QReCC
31F1 ScoreChatR1
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ChatR1LLM=Qwen-2.5-7b2026.01 | 31 | — | |
| OursLLM=Qwen-2.5-7b2026.01 | 30.4 | 64.6 | |
| ChatR1LLM=Qwen-2.5-3b2026.01 | 28 | — | |
| ClaudeLLM=Sonnet-3.52026.01 | 27 | — | |
| UniConvLLM=Mistral-2-7b2026.01 | 26.2 | — | |
| OursLLM=Qwen-2.5-3b2026.01 | 24.1 | 56.3 | |
| EvoRAGLLM=Qwen-2.5-7b2026.01 | 24 | — | |
| ChatQALLM=LLaMA-3-8b2026.01 | 23.7 | — | |
| ChatGPTLLM=GPT-3.52026.01 | 22.8 | — | |
| AgenticLMLLM=Qwen-3-8b2026.01 | 21.1 | 49.6 | |
| SFTLLM=Qwen-2.5-7b2026.01 | 19.1 | 54.3 | |
| REFRAGLLM=LLaMA-2-7b2026.01 | 17.4 | — | |
| SFTLLM=Qwen-2.5-3b2026.01 | 17 | 50.4 | |
| Search-R1LLM=Qwen-2.5-7b2026.01 | 8.6 | 60.3 | |
| AgenticLMLLM=Qwen-3-4b2026.01 | 7.9 | 46.3 | |
| Search-R1LLM=Qwen-2.5-3b2026.01 | 5.9 | 48.7 |