Update README.md (#1)
Browse files- Update README.md (fdfc8b18534d0442aedb70565ec929317702ba36)
Co-authored-by: Wenwen Gao <[email protected]>
README.md
CHANGED
|
@@ -36,7 +36,7 @@ Given a conversation with multiple turns between user and assistant, it rates th
|
|
| 36 |
8. **Complexity**: Intellectual depth required to write response (i.e. whether the response can be written by anyone with basic language competency or requires deep domain expertise).
|
| 37 |
9. **Verbosity**: Amount of detail included in the response, relative to what is asked for in the prompt.
|
| 38 |
|
| 39 |
-
The first four
|
| 40 |
|
| 41 |
|
| 42 |
HelpSteer Paper : [HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM](http://arxiv.org/abs/2311.09528)
|
|
|
|
| 36 |
8. **Complexity**: Intellectual depth required to write response (i.e. whether the response can be written by anyone with basic language competency or requires deep domain expertise).
|
| 37 |
9. **Verbosity**: Amount of detail included in the response, relative to what is asked for in the prompt.
|
| 38 |
|
| 39 |
+
The first four attributes are taken from the [Open Assistant](https://huggingface.co/datasets/OpenAssistant/oasst1) dataset while the others are taken from [HelpSteer](https://huggingface.co/datasets/nvidia/HelpSteer) dataset
|
| 40 |
|
| 41 |
|
| 42 |
HelpSteer Paper : [HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM](http://arxiv.org/abs/2311.09528)
|