Week 5

This week, the professor asked me to pass all the prompts in the Winobias dataset into various large language models. I did not know how to automate this as I have never used Python before. So, I started passing all of the prompts individually. I thought that it would help me notice a pattern better if I looked at the individual outputs from the LLM. Clearly, this was a bad idea. There were around 1600 prompts total and I also had to experiment with all 1600 of these in their third person plural version as well. I was able to do around 30 by the end of it.

When I spoke to my professor, he pointed another flaw with my method: I did not have any quantitative data. This was important in research. So, he helped me get started on the code for passing all of the prompts in at once. This made things a lot easier and we were able to finish our work a lot faster. We were also able to gwt some p[preliminary data.