Commit
•
5be112d
1
Parent(s):
04a5470
Update README.md
Browse files
README.md
CHANGED
@@ -4,6 +4,7 @@ datasets:
|
|
4 |
- newsmediabias/Bias-DeBiased
|
5 |
metrics:
|
6 |
- accuracy
|
|
|
7 |
---
|
8 |
### Model Card for MBIAS
|
9 |
|
@@ -61,9 +62,17 @@ The model can be accessed and used for text generation through the HuggingFace p
|
|
61 |
#### Performance Metrics
|
62 |
Performance metrics are provided for both pre-safety and post-safety intervention phases. The model has shown excellent results in improving the retention of contextual accuracy while reducing bias and toxicity levels compared to other versions and configurations.
|
63 |
|
64 |
-
|
65 |
-
Please cite the work as follows:
|
66 |
-
Ananya Raval, Veronica Chatrath, and Shaina Raza. "MBIAS: Enhancing Safety in Language Models While Retaining Contextual Accuracy."
|
67 |
|
68 |
-
|
69 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
- newsmediabias/Bias-DeBiased
|
5 |
metrics:
|
6 |
- accuracy
|
7 |
+
pipeline_tag: text-generation
|
8 |
---
|
9 |
### Model Card for MBIAS
|
10 |
|
|
|
62 |
#### Performance Metrics
|
63 |
Performance metrics are provided for both pre-safety and post-safety intervention phases. The model has shown excellent results in improving the retention of contextual accuracy while reducing bias and toxicity levels compared to other versions and configurations.
|
64 |
|
65 |
+
## Citation
|
|
|
|
|
66 |
|
67 |
+
If you use this work, please cite it as follows:
|
68 |
+
|
69 |
+
```bibtex
|
70 |
+
@article{raza2024mbias,
|
71 |
+
title={MBIAS: Mitigating Bias in Large Language Models While Retaining Context},
|
72 |
+
author={Shaina Raza and Ananya Raval and Veronica Chatrath},
|
73 |
+
year={2024},
|
74 |
+
eprint={2405.11290},
|
75 |
+
archivePrefix={arXiv},
|
76 |
+
primaryClass={cs.CL}
|
77 |
+
}
|
78 |
+
```
|