Spreadsheet Modeling Experiments Using GPTs on Small Problem Statements and the Wall Task

• URL: http://arxiv.org/abs/2604.25689v1
• Date: Tue, 28 Apr 2026 14:19:02 GMT
• Title: Spreadsheet Modeling Experiments Using GPTs on Small Problem Statements and the Wall Task
• Abstract summary: GPT-based tools can assist in building reusable analytical spreadsheet models.<n>We evaluate five GPT extensions and select Excel AI by pulsrai.com for detailed testing.<n>Results show that while Excel AI can produce well-structured models, it is inconsistent and often non-reproducible.
• Score: 3.6086016443500952
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning [58.75883713573783]
  Tool-Integrated Reasoning has emerged as a promising paradigm that incorporates tool call and execution within the reasoning trajectory.<n>We find that when the reasoning of the model conflicts with the tool results, the model tends to believe in its own reasoning.<n>We introduce Adaptive Tool Trust (ATTC), a framework that guides the model to adaptively choose to trust or ignore the tool results.
  arXiv  Detail & Related papers  (2026-04-09T14:14:37Z)
• AIDABench: AI Data Analytics Benchmark [62.45908988324612]
  AIDABench is a benchmark for evaluating AI systems on complex data analytics tasks in an end-to-end manner.<n>AIDABench encompasses 600+ diverse document analysis tasks across three core capability dimensions: question answering, data visualization, and file generation.<n>We evaluate 11 state-of-the-art models on AIDABench, spanning both proprietary (e.g., Claude Sonnet 4.5, Gemini 3 Pro Preview) and open-source (e.g., Qwen3-Max-2026-01-23-Thinking) families.
  arXiv  Detail & Related papers  (2026-02-27T08:58:05Z)
• SpreadsheetArena: Decomposing Preference in LLM Generation of Spreadsheet Workbooks [8.306042091008957]
  Large language models (LLMs) are increasingly tasked with producing and manipulating structured artifacts.<n>We introduce SpreadsheetArena, a platform for evaluating models' performance on the task.<n>We observe that stylistic, structural, and functional features of preferred spreadsheets vary substantially across use cases.
  arXiv  Detail & Related papers  (2026-02-16T14:24:36Z)
• One Model to Critique Them All: Rewarding Agentic Tool-Use via Efficient Reasoning [54.580646706013965]
  Reward models (RMs) play a critical role in aligning large language models with human preferences.<n>We introduce ToolRM, a family of lightweight generative RMs tailored for general tool-use scenarios.<n>To build these models, we propose a novel pipeline that constructs pairwise preference data using rule-based scoring and multidimensional sampling.
  arXiv  Detail & Related papers  (2025-10-30T06:08:27Z)
• Benchmark Dataset Generation and Evaluation for Excel Formula Repair with LLMs [3.4697197968922566]
  Large language models (LLMs) offer promising assistance by explaining formula errors.<n>This paper introduces a novel approach for constructing a benchmark dataset specifically designed for Excel formula repair.<n>Our pipeline integrates few-shot prompting with LLMs and employs a robust textitLLM-as-a-Judge validation framework.
  arXiv  Detail & Related papers  (2025-08-14T16:43:35Z)
• Small Language Models Need Strong Verifiers to Self-Correct Reasoning [69.94251699982388]
  Self-correction has emerged as a promising solution to boost the reasoning performance of large language models (LLMs) This work explores whether small (= 13B) language models (LMs) have the ability of self-correction on reasoning tasks with minimal inputs from stronger LMs.
  arXiv  Detail & Related papers  (2024-04-26T03:41:28Z)
• NL2Formula: Generating Spreadsheet Formulas from Natural Language Queries [29.33149993368329]
  This paper introduces a novel benchmark task called NL2Formula. The aim is to generate executable formulas that are grounded on a spreadsheet table, given a Natural Language (NL) query as input. We construct a comprehensive dataset consisting of 70,799 paired NL queries and corresponding spreadsheet formulas, covering 21,670 tables and 37 types of formula functions.
  arXiv  Detail & Related papers  (2024-02-20T05:58:05Z)
• TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks [75.1781376169951]
  Language models (LMs) can solve tasks such as answering questions about tables or images by writing programs. To enable better solutions without human labor, we ask code LMs to curate reusable high-level functions. We present TROVE, a training-free method of inducing a verifiable and efficient toolbox of functions.
  arXiv  Detail & Related papers  (2024-01-23T16:03:17Z)
• People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language Detection [35.89913036572029]
  It is imperative that NLP models are robust to spurious features. Past work has attempted to tackle such spurious features using training data augmentation. We assess if this task can be automated using generative NLP models.
  arXiv  Detail & Related papers  (2023-11-02T14:31:25Z)
• Struc-Bench: Are Large Language Models Really Good at Generating Complex Structured Data? [49.688233418425995]
  Struc-Bench is a comprehensive benchmark featuring prominent Large Language Models (LLMs) We propose two innovative metrics, P-Score (Prompting Score) and H-Score (Heuristical Score) Our experiments show that applying our structure-aware fine-tuning to LLaMA-7B leads to substantial performance gains.
  arXiv  Detail & Related papers  (2023-09-16T11:31:58Z)
• ChatGPT and Excel -- trust, but verify [0.0]
  This paper adopts a critical approach to ChatGPT, showing how its huge reach makes it a useful tool for people with simple requirements but a bad, even misleading guide to those with more complex problems which are more rarely present in the training data and even more rarely have straightforward solutions. It concludes with a practical guide for how to add an Excelscript button, with system and user prompts, to the ChatGPT API into the Excel desktop environment, supported by a blog post giving the technical details for those interested.
  arXiv  Detail & Related papers  (2023-08-31T20:21:02Z)
• Is Self-Repair a Silver Bullet for Code Generation? [68.02601393906083]
  Large language models have shown remarkable aptitude in code generation, but still struggle to perform complex tasks. Self-repair -- in which the model debugs and repairs its own code -- has recently become a popular way to boost performance. We analyze Code Llama, GPT-3.5 and GPT-4's ability to perform self-repair on problems taken from HumanEval and APPS.
  arXiv  Detail & Related papers  (2023-06-16T15:13:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.