Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.25689 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917444084301824 |
|---|---|
| author | Grossman, Thomas A. Chen, Yuan Datuashvili, Sopiko |
| author_facet | Grossman, Thomas A. Chen, Yuan Datuashvili, Sopiko |
| contents | This paper investigates how GPT-based tools can assist in building reusable analytical spreadsheet models. After a screening, we evaluate five GPT extensions and select Excel AI by pulsrai.com for detailed testing. Through structured experiments on simple problem statements, we assess Excel AI's performance against the ERFR criteria (each input in a cell; cell formulas; no hardwired numbers; labels; accurate). Results show that while Excel AI can produce well-structured models, it is inconsistent and often non-reproducible. We identify two central challenges - "the problem of confidence" and "the problem of workflow" - which highlight the need for skilled users to verify and adapt GPT-generated spreadsheets. Though GPTs show promise for generating draft models that may reduce development time or lower skill requirements, current tools remain unreliable for professional use. We conclude with recommendations for future research into prompt engineering, reproducibility, and larger-scale modeling tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_25689 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Spreadsheet Modeling Experiments Using GPTs on Small Problem Statements and the Wall Task Grossman, Thomas A. Chen, Yuan Datuashvili, Sopiko Software Engineering Artificial Intelligence This paper investigates how GPT-based tools can assist in building reusable analytical spreadsheet models. After a screening, we evaluate five GPT extensions and select Excel AI by pulsrai.com for detailed testing. Through structured experiments on simple problem statements, we assess Excel AI's performance against the ERFR criteria (each input in a cell; cell formulas; no hardwired numbers; labels; accurate). Results show that while Excel AI can produce well-structured models, it is inconsistent and often non-reproducible. We identify two central challenges - "the problem of confidence" and "the problem of workflow" - which highlight the need for skilled users to verify and adapt GPT-generated spreadsheets. Though GPTs show promise for generating draft models that may reduce development time or lower skill requirements, current tools remain unreliable for professional use. We conclude with recommendations for future research into prompt engineering, reproducibility, and larger-scale modeling tasks. |
| title | Spreadsheet Modeling Experiments Using GPTs on Small Problem Statements and the Wall Task |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2604.25689 |