8  Interpretability, Explainability and Bias

Week 8

Lecture: Techniques for interpretability in text classification; sources of bias and implications
Lab: Applying transformers-interpret and ferret for interpreting model predictions; visualising bias

8.1 Lecture

Content to be added.

8.2 Lab

Content to be added.

8.3 Readings

• Wan, Y. et al. (2023) ‘“Kelly is a Warm Person, Joseph is a Role Model”: Gender Biases in LLM-Generated Reference Letters’. arXiv. https://doi.org/10.48550/arXiv.2310.09219
• Rossi, L., Harrison, K. and Shklovski, I. (2024) ‘The Problems of LLM-generated Data in Social Science Research’, Sociologica, 18(2), pp. 145–168. https://doi.org/10.6092/issn.1971-8853/19576