Authors : Diya Punetha; Dipit Baidya

Volume/Issue : Volume 10 - 2025, Issue 11 - November

---

Google Scholar : https://tinyurl.com/4nu3f5eb

Scribd : https://tinyurl.com/yc2ndx4m

DOI : https://doi.org/10.38124/ijisrt/25nov482

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 30 to 40 days to display the article.

---

Abstract : Spreadsheets are indispensable tools for managing data, especially for those unfamiliar with advanced functions or coding. By enabling users to interact with Excel through intuitive, conversational commands—such as “summarize sales by region” or “predict next quarter’s trends”—the proposed system translates natural language inputs into precise spreadsheet operations. Our approach leverages advanced language models to interpret user intent, execute complex formulas, generate charts, and even debug errors, all while maintaining Excel’s core functionality. Preliminary results demonstrate significant time savings and improved user confidence, suggesting that AI-enhanced Excel could democratize data manipulation and empower nontechnical users to harness the full potential of spreadsheets.

Keywords : Artificial Intelligence, Natural Language Processing, Microsoft Excel, Spreadsheet Automation, Data Analysis, User Interaction, Language Models, Productivity Enhancement, Data Visualization, Error Debugging.

References :

1. H. Joshi, A. Ebenezer, J. Cambronero, S. Gulwani, A. Kanade, V. Le, I. Radiček, and G. Verbruggen, “FLAME: A small language model for spreadsheet formulas,” in *Proc. AAAI Conf. Artificial Intelligence*, vol. 38, pp. 12995–13003, 2024. :contentReference[oaicite:1]{index=1}
2. W. Zhao, Z. Hou, S. Wu, Y. Gao, H. Dong, Y. Wan, H. Zhang, Y. Sui, and H. Zhang, “NL2Formula: Generatingspreadsheet   formulas   from   natural   language   queries,”   *arXiv*,   Feb.   20,   2024. :contentReference[oaicite:2]{index=2}
3. Y. Tian, J. Zhao, H. Dong, J. Xiong, S. Xia, M. Zhou, Y. Lin, J. Cambronero, Y. He, S. Han, and D. Zhang, “SpreadsheetLLM:  Encoding                  spreadsheets         for          large       language               models,” *arXiv*,  Jul.      12,          2024. :contentReference[oaicite:3]{index=3}
4. J. Payan, S. Mishra, M. Singh, C. Negreanu, C. Poelitz, C. Baral, S. Roy, R. Chakravarthy, B. Van Durme, and E. Nouri, “InstructExcel: A benchmark for natural language instruction in Excel,” *Findings of ACL: EMNLP*, Singapore, Dec. 2023, pp. 4026–4043. :contentReference[oaicite:4]{index=4}
5. S. Xia, J. Xiong, H. Dong, J. Zhao, Y. Tian, M. Zhou, Y. He, S. Han, and D. Zhang, “Vision language models for spreadsheet understanding: challenges and opportunities,” in *Advances in Language and Vision Research (ALVR)*, 2024, pp. 116–128. :contentReference[oaicite:5]{index=5}
6. H. Li, J. Su, Y. Chen, Q. Li, and Z.-X. Zhang, “SheetCopilot: Bringing software productivity to the next level through large language models,” *NeurIPS*, 2023. :contentReference[oaicite:6]{index=6}
7. P. Li, Y. He, D. Yashar, W. Cui, S. Ge, H. Zhang, D. Rifinski Fainman, D. Zhang, and S. Chaudhuri, “TableGPT: Table-tuned GPT for diverse table tasks,” *arXiv*, Oct. 2023. :contentReference[oaicite:7]{index=7}
8. Y. Sui, M. Zhou, M. Zhou, S. Han, and D. Zhang, “GPT4Table: Can large language models understand structured         table    data?      A             benchmark            and         empirical               study,”   *arXiv*,                May        2023. :contentReference[oaicite:8]{index=8}
9. A. Singha, J. Cambronero, S. Gulwani, V. Le, and C. Parnin, “Tabular representation, noisy operators, and                impacts      on           table       structure  understanding   tasks        in            LLMs,”  *arXiv*,  Oct. 2023.  :contentReference[oaicite:10]{index=10}
10. S. Tang, Y. Zong, Y. Zhao, A. Cohan, and M. Gerstein, “Struc-bench: Are large language models really good at generating complex structured data?” *arXiv*, Sept. 2023. :contentReference[oaicite:11]{index=11}
11. X. Wu, H. Chen, C. Bu, S. Ji, Z. Zhang, and V. Sheng, “HUSS: A heuristic method for understanding the semantic structure of spreadsheets,” *Data Intelligence*, vol. 5, no. 3, pp. 537–559, 2023. :contentReference[oaicite:12]{index=12}
12. T. Zhang, X. Yue, Y. Li, and H. Sun, “TableLlama: Towards open large generalist models for tables,” *arXiv*, Nov. 2023. :contentReference[oaicite:13]{index=13}
13. A.Garg and B. Garg, "A robust and novel regression based fuzzy time series algorithm for prediction of rice yield," in 2017 International Conference on Intelligent Communication and  Computational  Techniques  (ICCT),  Jaipur,  India,  2017,  pp.  48-54,  doi: 10.1109/INTELCCT.2017.8324019.
14. B. Garg, M. M. S. Beg and A. Q. Ansari, "Employing genetic algorithm to optimize OWA-fuzzy forecasting model," 2011 Third World Congress on Nature and Biologically Inspired Computing, Salamanca, Spain, 2011, pp. 285-290, doi: 10.1109/NaBIC.2011.6089609.