Evaluating large language models for accuracy incentivizes hallucinations
- Journal:
- Nature
- Published:
- Affiliations:
- 3
- Authors:
- 4
| Institutions | Authors | Share |
|---|---|---|
| OpenAI, United States of America (USA) | 0.75 | |
| Georgia Institute of Technology (Georgia Tech), United States of America (USA) | 0.25 |