Question Answering on QA
59.5AccuracyDPS
Evaluation Results
| Method | Links | |
|---|---|---|
| DPSLLM Backbone=Gemini-1.5 Flash2025.02 | 59.5 | |
| DPSLLM Backbone=GPT-3.5 Turbo2025.02 | 58.9 | |
| OPROLLM Backbone=Gemini-1.5 Flash2025.02 | 58.9 | |
| OPROLLM Backbone=GPT-3.5 Turbo2025.02 | 58.3 | |
| APELLM Backbone=Gemini-1.5 Flash2025.02 | 58.1 | |
| DPSLLM Backbone=Llama-3.1 70B2025.02 | 58.1 | |
| N/ALLM Backbone=GPT-3.5 Turbo2025.02 | 57.8 | |
| APELLM Backbone=GPT-3.5 Turbo2025.02 | 57.5 | |
| OPROLLM Backbone=Llama-3.1 70B2025.02 | 57.4 | |
| APELLM Backbone=Llama-3.1 70B2025.02 | 57.1 | |
| N/ALLM Backbone=Gemini-1.5 Flash2025.02 | 56.9 | |
| N/ALLM Backbone=Llama-3.1 70B2025.02 | 56.3 |