Question Answering on QuALITY ZeroSCROLLS leaderboard (test)
72.8AccuracyChatGPT (ER)
Evaluation Results
| Method | Links | |
|---|---|---|
| ChatGPT (ER)Retrieval method=Enhanced Retrieval (ER) with NARCO, Context limit=1.5k2024.02 | 72.8 | |
| ChatGPT (R)Retrieval method=Baseline (R), Context limit=1.5k2024.02 | 70.8 | |
| Llama2-70B (R)*Retrieval method=Baseline (R), Context limit=1.5k, Reported by=Xu et al. (2024)2024.02 | 70.3 | |
| ChatGPT*source=ZeroSCROLLS organizers2024.02 | 66.6 |