Technical Challenges in Maintaining Tax Prep Software with Large Language Models
This addresses the challenge of timely and accurate software updates for tax professionals and taxpayers, but it is incremental as it applies existing LLMs to a new domain-specific task.
The paper tackles the problem of maintaining tax preparation software by proposing to use Large Language Models to automatically translate IRS tax law amendments into code differentials, aiming to automate the currently manual and error-prone process.
As the US tax law evolves to adapt to ever-changing politico-economic realities, tax preparation software plays a significant role in helping taxpayers navigate these complexities. The dynamic nature of tax regulations poses a significant challenge to accurately and timely maintaining tax software artifacts. The state-of-the-art in maintaining tax prep software is time-consuming and error-prone as it involves manual code analysis combined with an expert interpretation of tax law amendments. We posit that the rigor and formality of tax amendment language, as expressed in IRS publications, makes it amenable to automatic translation to executable specifications (code). Our research efforts focus on identifying, understanding, and tackling technical challenges in leveraging Large Language Models (LLMs), such as ChatGPT and Llama, to faithfully extract code differentials from IRS publications and automatically integrate them with the prior version of the code to automate tax prep software maintenance.