What Job Is This, Anyway?: Using LLMs to Classify USAJobs Data Scientist Listings by Abigail Haddad

Visit https://rstats.ai/gov to learn more.

Abstract: Navigating the federal job market begins with finding appropriate job listings. But for data professionals, discrepancies often arise between the content of the listing - that is, the duties of the job - and either the job title or the occupational code, making this step more difficult. In this presentation, I discuss using a Large Language Model (LLM) to generate new job titles for listings in occupational code 1560, Data Science. I'll show examples of listings with mismatches between the official job title and the one generated by GPT-3.5 and discuss the potential uses of this for applicants and agencies. I'll also highlight the advantages of using Marvin, a library that lets you use LLMs to solve Natural Language Processing problems by just writing documentation rather than code.

Bio: Abigail Haddad is a data scientist who has spent most of the last 14 years doing research and data science for the Department of Defense, including as a Department of the Army civilian. She’s interested in the capabilities of generative AI for both code generation and Natural Language Processing. Her hobbies include analyzing federal job listings and co-organizing Data Science DC. She blogs at Present of Coding on Substack.

Twitter:   / abbystat  

Presented at the 2023 Government & Public Sector R Conference (October 19, 2023)