exp: Research difference metrics to measure performance for LLM code-to-documentation generation.

[anujsinha3]

As of date, AutoDoc code-to-documentation LLM has very few code examples to test the performance of our model.

This task involves the research and comparison of the probable metrics that can be used to quantify the performance of the code-to-documentation LLM model.

A few of the example metrics that are currently used:
https://uwnetid.sharepoint.com/sites/og_ssec_escience/_layouts/15/Doc.aspx?sourcedoc={80d21348-b124-4e69-a17d-542a8cfca496}&action=edit&wd=target%28Untitled%20Section.one%7C4a55f2ee-6dcd-42d4-aaac-82c7bcc49788%2FLiterature%20Survey%7C18d2f5b8-af8b-475d-b4ca-f8731dda9d11%2F%29&wdorigin=NavigationUrl

Task Completion is dependent on the provisioning of training data from the AutoRA team.