Spaces:
No application file
No application file
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Active UltraFeedback
|
| 2 |
|
| 3 |
**Active UltraFeedback** is a scalable pipeline for generating high-quality preference datasets to align large language models (LLMs). We leverage **uncertainty quantification** and **active learning** to annotate only the most informative samples, drastically reducing costs while beating standard baselines.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
title: ActiveUltraFeedback
|
| 4 |
+
short_description: Sample-Efficient RLHF Preference data generation
|
| 5 |
+
papers: 2603.09692
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
# Active UltraFeedback
|
| 9 |
|
| 10 |
**Active UltraFeedback** is a scalable pipeline for generating high-quality preference datasets to align large language models (LLMs). We leverage **uncertainty quantification** and **active learning** to annotate only the most informative samples, drastically reducing costs while beating standard baselines.
|