Update README.md
Browse files
README.md
CHANGED
|
@@ -116,11 +116,11 @@ I trust that the path we have chosen will lead us to a brighter tomorrow.
|
|
| 116 |
One of the primary limitations faced with this approach was the difficulty of generating synthetic data. It proved hard to find historical documents from a certain era and took a large amount of compute and time to generate the synthetic first-person narratives for these documents. Future work would entail creating more data for the model to train on, improving results further. The other primary limitation from this model is the lack of creative introductions in the model’s responses. The model has shown to always start with a sentence or phrase of the year and date. While this sets the scene, the model could be improved to have more creative beginnings to the narratives.
|
| 117 |
|
| 118 |
**Works Cited** <br />
|
| 119 |
-
Hendrycks, D., Burns, C., Basart, S., Zou, A., Mazeika, M., Song, D., & Steinhardt, J
|
| 120 |
-
(2021). Measuring Massive Multitask Language Understanding
|
| 121 |
-
(arXiv:2109.07958). arXiv. https://arxiv.org/abs/2109.07958
|
| 122 |
-
Zellers, R., Holtzman, A., Rashkin, H., Bisk, Y., Farhadi, A., Roesner, F., & Choi, Y
|
| 123 |
-
|
| 124 |
-
(arXiv:1905.07830). arXiv. https://arxiv.org/abs/1905.07830
|
| 125 |
-
Lin, B. Y., Tan, C., Jiang, M., & Han, X. (2020). TruthfulQA: Measuring How Models
|
| 126 |
-
Mimic Human Falsehoods
|
|
|
|
| 116 |
One of the primary limitations faced with this approach was the difficulty of generating synthetic data. It proved hard to find historical documents from a certain era and took a large amount of compute and time to generate the synthetic first-person narratives for these documents. Future work would entail creating more data for the model to train on, improving results further. The other primary limitation from this model is the lack of creative introductions in the model’s responses. The model has shown to always start with a sentence or phrase of the year and date. While this sets the scene, the model could be improved to have more creative beginnings to the narratives.
|
| 117 |
|
| 118 |
**Works Cited** <br />
|
| 119 |
+
Hendrycks, D., Burns, C., Basart, S., Zou, A., Mazeika, M., Song, D., & Steinhardt, J.<br />
|
| 120 |
+
(2021). Measuring Massive Multitask Language Understanding<br />
|
| 121 |
+
(arXiv:2109.07958). arXiv. https://arxiv.org/abs/2109.07958<br />
|
| 122 |
+
Zellers, R., Holtzman, A., Rashkin, H., Bisk, Y., Farhadi, A., Roesner, F., & Choi, Y.<br />
|
| 123 |
+
(2019). HellaSwag: Can a Machine Really Finish Your Sentence?<br />
|
| 124 |
+
(arXiv:1905.07830). arXiv. https://arxiv.org/abs/1905.07830<br />
|
| 125 |
+
Lin, B. Y., Tan, C., Jiang, M., & Han, X. (2020). TruthfulQA: Measuring How Models<br />
|
| 126 |
+
Mimic Human Falsehoods<br /> (arXiv:2009.03300). arXiv. https://arxiv.org/abs/2009.03300
|