Question Answering on HotpotQA Distractor
75Exact Match (EM)CLAUSE
Evaluation Results
| Method | Links | |
|---|---|---|
| CLAUSEFamily=Ours, Reader Model=GPT-OSS-120B2025.09 | 75 | |
| CLAUSEFamily=Ours, LLM Reader=LLaMA3.3-70B2025.09 | 73.5 | |
| CLAUSEFamily=Ours2025.09 | 71.7 | |
| KG-AgentFamily=Agent-based, Reader Model=GPT-OSS-120B2025.09 | 69.8 | |
| KG-AgentFamily=Agent-based, LLM Reader=LLaMA3.3-70B2025.09 | 69.3 | |
| Hybrid RAGFamily=RAG-based, Reader Model=GPT-OSS-120B2025.09 | 68.9 | |
| KG-AgentFamily=Agent-based (Qwen3-32B)2025.09 | 68.7 | |
| Hybrid RAGFamily=RAG-based, LLM Reader=LLaMA3.3-70B2025.09 | 66.7 | |
| AutoGenFamily=Agent-based, Reader Model=GPT-OSS-120B2025.09 | 66.6 | |
| Hybrid RAGFamily=RAG-based (Qwen3-32B)2025.09 | 66 | |
| Vanilla RAGFamily=RAG-based, Reader Model=GPT-OSS-120B2025.09 | 65.9 | |
| ReActFamily=Agent-based, Reader Model=GPT-OSS-120B2025.09 | 65.5 | |
| AutoGenFamily=Agent-based, LLM Reader=LLaMA3.3-70B2025.09 | 65.2 | |
| ReActFamily=Agent-based, LLM Reader=LLaMA3.3-70B2025.09 | 65 | |
| AutoGenFamily=Agent-based (Qwen3-32B)2025.09 | 64 | |
| Vanilla RAGFamily=RAG-based, LLM Reader=LLaMA3.3-70B2025.09 | 63.8 | |
| ReActFamily=Agent-based (Qwen3-32B)2025.09 | 63.5 | |
| Vanilla RAGFamily=RAG-based (Qwen3-32B)2025.09 | 62.1 | |
| Graph-of-ThoughtsFamily=Agent-based, Reader Model=GPT-OSS-120B2025.09 | 61 | |
| Graph-of-ThoughtsFamily=Agent-based, LLM Reader=LLaMA3.3-70B2025.09 | 60.3 | |
| Graph-of-ThoughtsFamily=Agent-based (Qwen3-32B)2025.09 | 59.2 | |
| GraphRAGFamily=RAG-based, Reader Model=GPT-OSS-120B2025.09 | 53.5 | |
| GraphRAGFamily=RAG-based, LLM Reader=LLaMA3.3-70B2025.09 | 51.4 | |
| LightRAGFamily=RAG-based, Reader Model=GPT-OSS-120B2025.09 | 50.7 | |
| GraphRAGFamily=RAG-based (Qwen3-32B)2025.09 | 50.1 | |
| LightRAGFamily=RAG-based, LLM Reader=LLaMA3.3-70B2025.09 | 48.6 | |
| GPT-OSS-120BFamily=Pretrained-LLMs2025.09 | 44.5 | |
| LightRAGFamily=RAG-based (Qwen3-32B)2025.09 | 44.3 | |
| LLaMA3.3-70BFamily=Pretrained-LLMs2025.09 | 41 | |
| Qwen3-32BFamily=Pretrained-LLMs2025.09 | 37.9 |