📊 Showing 4 results | 📏 Metric: CIDEr
| Rank | Model | Paper | CIDEr | Date | Code |
|---|---|---|---|---|---|
| 1 | BART (TextBox 2.0) | TextBox 2.0: A Text Generation Library with Pre-trained Language Models | 28.18 | 2022-12-26 | 📦 RUCAIBox/TextBox |
| 2 | UniLM | CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning | 14.92 | 2019-11-09 | 📦 INK-USC/CommonGen 📦 allenai/CommonGen-Eval 📦 varshakr24/CommonsenseReasoning |
| 3 | BART | The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics | 0.30 | 2021-02-02 | - |
| 4 | T5 | The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics | 0.29 | 2021-02-02 | - |