Table Selection on BIRD 2023 (test)
5.3Avg #tablesARM
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| ARMSelector=Llama-3.1-8B-Instruct, Dense Retrieval=UAE-Large-V12026.01 | 5.3 | 40.4 | 95.4 | 53.5 | 90.9 | |
| DR@5Selector=Llama-3.1-8B-Instruct, Dense Retrieval=UAE-Large-V12026.01 | 5 | 34.9 | 91.9 | 49.4 | 83 | |
| DRR@5Selector=Llama-3.1-8B-Instruct, Dense Retrieval=UAE-Large-V12026.01 | 5 | 35.3 | 92.7 | 49.9 | 84.7 | |
| JAR@5Selector=Llama-3.1-8B-Instruct, Dense Retrieval=UAE-Large-V12026.01 | 5 | 35.5 | 92.9 | 50.1 | 86 | |
| DR@5Selector=Qwen-2.5-7B-Instruct, Dense Retrieval=UAE-Large-V12026.01 | 5 | 35.2 | 92.5 | 49.8 | 84.2 | |
| DRR@5Selector=Qwen-2.5-7B-Instruct, Dense Retrieval=UAE-Large-V12026.01 | 5 | 35.2 | 92.7 | 49.8 | 84.6 | |
| JAR@5Selector=Qwen-2.5-7B-Instruct, Dense Retrieval=UAE-Large-V12026.01 | 5 | 35.5 | 92.8 | 50.1 | 86 | |
| ReActSelector=Llama-3.1-8B-Instruct, Dense Retrieval=UAE-Large-V12026.01 | 4.8 | 43.1 | 93 | 55.6 | 86.1 | |
| CORE-TSelector=Llama-3.1-8B-Instruct, Dense Retrieval=UAE-Large-V12026.01 | 4.2 | 48.9 | 94.9 | 61.5 | 90.2 | |
| ARMSelector=Qwen-2.5-7B-Instruct, Dense Retrieval=UAE-Large-V12026.01 | 3.5 | 58.7 | 92.3 | 67.9 | 84.2 | |
| ReActSelector=Qwen-2.5-7B-Instruct, Dense Retrieval=UAE-Large-V12026.01 | 3.3 | 65.6 | 90.5 | 71.6 | 81.3 | |
| CORE-TSelector=Qwen-2.5-7B-Instruct, Dense Retrieval=UAE-Large-V12026.01 | 3.1 | 61.9 | 93.3 | 71.4 | 86.3 |