Chain-of-Thought Generation on e-SNLI (test)
3.49GPT-4 ScoreGold
Evaluation results
| Method | Links | |
|---|---|---|
| GoldSelf-consistency=true2024.03 | 3.49 | |
| DSSSelf-consistency=false2024.03 | 3.24 | |
| DSSSelf-consistency=true2024.03 | 3.18 | |
| MI-based distillationSelf-consistency=true2024.03 | 3.17 | |
| MI-based distillationSelf-consistency=false2024.03 | 3.03 | |
| GoldSelf-consistency=false2024.03 | 2.42 |