Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2504.18693 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913808220422144 |
|---|---|
| author | Gogani-Khiabani, Sina Dewangan, Varsha Olson, Nina Trivedi, Ashutosh Tizpaz-Niari, Saeid |
| author_facet | Gogani-Khiabani, Sina Dewangan, Varsha Olson, Nina Trivedi, Ashutosh Tizpaz-Niari, Saeid |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_18693 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Technical Challenges in Maintaining Tax Prep Software with Large Language Models Gogani-Khiabani, Sina Dewangan, Varsha Olson, Nina Trivedi, Ashutosh Tizpaz-Niari, Saeid Software Engineering Artificial Intelligence https://www.irs.gov/statistics/fourteenth-annual-irs-tpc-joint-research-conference-on-tax-administration 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. |
| title | Technical Challenges in Maintaining Tax Prep Software with Large Language Models |
| topic | Software Engineering Artificial Intelligence https://www.irs.gov/statistics/fourteenth-annual-irs-tpc-joint-research-conference-on-tax-administration |
| url | https://arxiv.org/abs/2504.18693 |