Update README.md
Browse files
README.md
CHANGED
|
@@ -78,6 +78,7 @@ print(response)
|
|
| 78 |
|
| 79 |
### Further Details, Social Impacts, Bias, and Limitations
|
| 80 |
Please refer to our [paper](https://arxiv.org/abs/2212.10465).
|
|
|
|
| 81 |
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. 2021](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. 2021](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)). Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups.
|
| 82 |
|
| 83 |
## Additional Information
|
|
|
|
| 78 |
|
| 79 |
### Further Details, Social Impacts, Bias, and Limitations
|
| 80 |
Please refer to our [paper](https://arxiv.org/abs/2212.10465).
|
| 81 |
+
Cosmo is mostly trained on social chitchat. Therefore, we do not encourage having knowledge-intensive conversations (e.g., science, medical issues, law).
|
| 82 |
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. 2021](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. 2021](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)). Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups.
|
| 83 |
|
| 84 |
## Additional Information
|