Cultural Question Answering on CLIcK
0.5888AccuracyCORAL (QWEN3-235B)
Evaluation Results
| Method | Links | |
|---|---|---|
| CORAL (QWEN3-235B)Generator Model=LLAMA-3.2-3B-INSTRUCT, RAG Strategy=CORAL, Planner/Critic Model=QWEN3-235B2026.04 | 0.5888 | |
| CORAL (GPT-OSS-120B)Generator Model=LLAMA-3.2-3B-INSTRUCT, RAG Strategy=CORAL, Planner/Critic Model=GPT-OSS-120B2026.04 | 0.5866 | |
| tRAGGenerator Model=LLAMA-3.2-3B-INSTRUCT, RAG Strategy=tRAG2026.04 | 0.5606 | |
| crossRAGGenerator Model=LLAMA-3.2-3B-INSTRUCT, RAG Strategy=crossRAG2026.04 | 0.5375 | |
| monoRAGGenerator Model=LLAMA-3.2-3B-INSTRUCT, RAG Strategy=monoRAG2026.04 | 0.5353 | |
| multiRAGGenerator Model=LLAMA-3.2-3B-INSTRUCT, RAG Strategy=multiRAG2026.04 | 0.5078 | |
| Non-RAGGenerator Model=LLAMA-3.2-3B-INSTRUCT, RAG Strategy=None2026.04 | 0.481 |