Question Answering on StrategyQA (EM & F1)
89.34EMCD
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| CDModel=FLAN-T5-3B2024.02 | 89.34 | 89.34 | — | — | |
| COIECDModel=FLAN-T5-3B2024.02 | 88.78 | 88.78 | — | — | |
| CADModel=FLAN-T5-3B2024.02 | 88.69 | 88.69 | — | — | |
| RegularModel=FLAN-T5-3B2024.02 | 87.07 | 87.07 | — | — | |
| SCModel=FLAN-T5-3B2024.02 | 86.81 | 86.81 | — | — | |
| COIECDModel=LLaMA2-13B2024.02 | 85.76 | 85.76 | — | — | |
| CADModel=LLaMA2-13B2024.02 | 85.5 | 85.5 | — | — | |
| CDModel=LLaMA2-13B2024.02 | 83.58 | 83.58 | — | — | |
| RegularModel=LLaMA2-13B2024.02 | 81.09 | 81.09 | — | — | |
| SCModel=LLaMA2-13B2024.02 | 81.05 | 81.05 | — | — | |
| DioRRetrieval Strategy=BM25, Backbone=LLaMA2-7B-CHAT2025.04 | 65.9 | 65.9 | 65.9 | 65.9 | |
| DioRRetrieval Strategy=SBERT, Backbone=LLaMA2-7B-CHAT2025.04 | 65.4 | 65.4 | 65.4 | 65.4 | |
| DraginRetrieval Strategy=SBERT, Backbone=LLaMA2-7B-CHAT2025.04 | 64.5 | 64.5 | 64.5 | 64.5 | |
| DraginRetrieval Strategy=BM25, Backbone=LLaMA2-7B-CHAT2025.04 | 63.9 | 63.9 | 63.9 | 63.9 | |
| DioRRetrieval Strategy=SGPT, Backbone=LLaMA2-7B-CHAT2025.04 | 61.6 | 61.6 | 61.6 | 61.6 | |
| DraginRetrieval Strategy=SGPT, Backbone=LLaMA2-7B-CHAT2025.04 | 60.4 | 60.4 | 60.4 | 60.4 | |
| COIECDModel=OPT-6.7B2024.02 | 53.84 | 53.84 | — | — | |
| CADModel=OPT-6.7B2024.02 | 53.1 | 53.1 | — | — | |
| RegularModel=OPT-6.7B2024.02 | 47.51 | 47.51 | — | — | |
| CDModel=OPT-6.7B2024.02 | 46.99 | 46.99 | — | — | |
| SCModel=OPT-6.7B2024.02 | 46.64 | 46.64 | — | — |