Chain-of-Thought Generation on CQA (test)
4.11GPT-4 ScoreGold
Evaluation results
| Method | Links | |
|---|---|---|
| GoldSelf-consistency=true2024.03 | 4.11 | |
| GoldSelf-consistency=false2024.03 | 3.95 | |
| MI-based distillationSelf-consistency=false2024.03 | 3.7 | |
| DSSSelf-consistency=true2024.03 | 3.64 | |
| MI-based distillationSelf-consistency=true2024.03 | 3.63 | |
| DSSSelf-consistency=false2024.03 | 3.6 |