About
Project
This package was developed as part of a master’s thesis on the MSc in Cognitive Science at Aarhus University. With this package, I hope to contribute to the development of methods for evaluating the use of LLMs.
The main contribution is refining and wrapping existing methods into a coherent test suite. Additionally, we have introduced our own evaluation and visualization functions to present the results of various metrics in a cohesive manner.
Contact
If you have any questions regarding the project or the code implementation, feel free to contact someone@example.com.
GenDa Lens is licensed under MIT and available on GitHub.
Acknowledgements
This project uses code from three already implemented frameworks for quantifying gender bias in Danish. While all externally authored code is properly attributed in the repository’s scripts, we would also like to acknowledge the authors of the work we draw on:
- Reference 1: Author, A. A. (Year). Title of the article. Journal Title, 10(2), 123–145. https://doi.org/10.0000/xyz123
- Reference 2: Author, B. B., & Author, C. C. (Year). Another work. Publisher. https://doi.org/10.0000/abc456
- Reference 3: Author, D. D. (Year). Yet another reference. Conference Proceedings. https://doi.org/10.0000/def789
- Reference 4: Organization E. (Year). Document title. Retrieved from https://doi.org/10.0000/ghi012