Metric: F1 (R16) (higher is better)
| # | Model↕ | F1 (R16)▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | MvP | 72.76 | No | MvP: Multi-view Prompting Improves Aspect Sentim... | 2023-05-22 | Code |
| 2 | Paraphrase | 71.97 | No | Aspect Sentiment Quad Prediction as Paraphrase G... | 2021-10-02 | Code |
| 3 | LEGO-ABSA (multi-task) | 71.8 | Yes | - | - | - |
| 4 | DLO | 71.79 | No | Improving Aspect Sentiment Quad Prediction via T... | 2022-10-19 | Code |
| 5 | MvP (multi-task) | 70.18 | Yes | MvP: Multi-view Prompting Improves Aspect Sentim... | 2023-05-22 | Code |
| 6 | Gemma-3-27B (50-shot, self-consistency learning) | 68.53 | No | Do we still need Human Annotators? Prompting Lar... | 2025-02-18 | Code |
| 7 | GAS | 68.31 | No | - | - | Code |
| 8 | Gemma-3-27B (10-shot, self-consistency learning) | 66.75 | No | Do we still need Human Annotators? Prompting Lar... | 2025-02-18 | Code |
| 9 | TAS-BERT | 65.89 | No | Aspect Sentiment Quad Prediction as Paraphrase G... | 2021-10-02 | Code |
| 10 | ChatGPT (gpt-3.5-turbo, few-shot) | 46.51 | No | MvP: Multi-view Prompting Improves Aspect Sentim... | 2023-05-22 | Code |
| 11 | ChatGPT (gpt-3.5-turbo, zero-shot) | 34.08 | No | MvP: Multi-view Prompting Improves Aspect Sentim... | 2023-05-22 | Code |