# regardv3

**Repository Path**: modelee/regardv3

## Basic Information

- **Project Name**: regardv3
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 4
- **Forks**: 0
- **Created**: 2023-05-24
- **Last Updated**: 2025-07-29

## Categories & Tags

**Categories**: llm

**Tags**: None

## README

---
license: cc-by-4.0
---

# BERT Regard classification model 

This model is the result of a project entitled [Towards Controllable Biases in Language Generation](https://github.com/ewsheng/controllable-nlg-biases). It consists of a BERT classifier (no ensemble) trained on 1.7K samples of biased language. 

*Regard*  measures language polarity towards and social perceptions of a demographic (compared to sentiment, which only measures overall language polarity).

### BibTeX entry and citation info

```bibtex
@article{sheng2019woman,
  title={The woman worked as a babysitter: On biases in language generation},
  author={Sheng, Emily and Chang, Kai-Wei and Natarajan, Premkumar and Peng, Nanyun},
  journal={arXiv preprint arXiv:1909.01326},
  year={2019}
}
```