Question Answering on Story
46.7Exact Match (EM)T^2RAG
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| T^2RAGInference LLM=Gemini-2.5-flash2025.08 | 46.7 | 59.5 | |
| RAPTORInference LLM=Gemini-2.5-flash2025.08 | 46.2 | 59 | |
| RAPTORInference LLM=GPT-4o-mini2025.08 | 44.8 | 59.6 | |
| HippoRAG2Inference LLM=GPT-4o-mini2025.08 | 41.2 | 58.3 | |
| IRCoTInference LLM=Gemini-2.5-flash2025.08 | 40.3 | 57.3 | |
| T^2RAGInference LLM=GPT-4o-mini2025.08 | 38.7 | 50.1 | |
| IRCoTInference LLM=GPT-4o-mini2025.08 | 36.1 | 51.8 | |
| HippoRAG2Inference LLM=Gemini-2.5-flash2025.08 | 33.1 | 44.1 | |
| StandardInference LLM=Gemini-2.5-flash2025.08 | 31 | 42.2 | |
| BM25Inference LLM=GPT-4o-mini2025.08 | 29 | 38.5 | |
| StandardInference LLM=GPT-4o-mini2025.08 | 27.3 | 60.1 | |
| BM25Inference LLM=Gemini-2.5-flash2025.08 | 26.2 | 35.3 | |
| NORInference LLM=GPT-4o-mini2025.08 | 11.5 | 18.9 | |
| NORInference LLM=Gemini-2.5-flash2025.08 | 10.3 | 17.1 |