| Autor: |
Agarwal, Arav, Mittal, Karthik, Doyle, Aidan, Sridhar, Pragnya, Wan, Zipiao, Doughty, Jacob Arthur, Savelka, Jaromir, Sakr, Majd |
| Rok vydání: |
2024 |
| Předmět: |
|
| Druh dokumentu: |
Working Paper |
| DOI: |
10.1145/3626253.3635608 |
| Popis: |
We conduct a preliminary study of the effect of GPT's temperature parameter on the diversity of GPT4-generated questions. We find that using higher temperature values leads to significantly higher diversity, with different temperatures exposing different types of similarity between generated sets of questions. We also demonstrate that diverse question generation is especially difficult for questions targeting lower levels of Bloom's Taxonomy. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
