ChatGPT and Excel -- trust, but verify

• URL: http://arxiv.org/abs/2309.00120v1
• Date: Thu, 31 Aug 2023 20:21:02 GMT
• Title: ChatGPT and Excel -- trust, but verify
• Authors: Patrick O'Beirne
• Abstract summary: 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.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 works through four exercises in creating lookup formulas using chatbots, showing the need to test the offered solutions. They are a simple lookup, a lookup to the left, a match of two values at the same time, and intentionally confusing the models by using common language with technical meaning in Excel. 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.

Related papers

• Auto-Formula: Recommend Formulas in Spreadsheets using Contrastive Learning for Table Representations [36.2969566996675]
  We develop an Auto-Formula system that can accurately predict formulas that users want to author in a target spreadsheet cell. We use contrastive-learning techniques inspired by "similar-face recognition" from compute vision.
  arXiv  Detail & Related papers  (2024-04-19T03:28:18Z)
• 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)
• InstructExcel: A Benchmark for Natural Language Instruction in Excel [72.018640505825]
  This work investigates whether Large Language Models can generate code that solves Excel specific tasks provided via natural language user instructions. Our benchmark includes over 10k samples covering 170+ Excel operations across 2,000 publicly available Excel spreadsheets. We observe that (1) using GPT-4 over GPT-3.5, (2) providing more in-context examples, and (3) dynamic prompting can help improve performance on this benchmark.
  arXiv  Detail & Related papers  (2023-10-23T02:00:55Z)
• Eliciting Human Preferences with Language Models [56.68637202313052]
  Language models (LMs) can be directed to perform target tasks by using labeled examples or natural language prompts. We propose to use *LMs themselves* to guide the task specification process. We study GATE in three domains: email validation, content recommendation, and moral reasoning.
  arXiv  Detail & Related papers  (2023-10-17T21:11:21Z)
• Experimenting with ChatGPT for Spreadsheet Formula Generation: Evidence of Risk in AI Generated Spreadsheets [0.0]
  Large Language Models (LLM) have become sophisticated enough that complex computer programs can be created through interpretation of plain English sentences. This paper presents a series of experiments with ChatGPT to explore the tool's ability to produce valid spreadsheet formulae.
  arXiv  Detail & Related papers  (2023-08-31T19:31:32Z)
• Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models [55.11367495777145]
  ChatGPT is attracting a cross-field interest as it provides a language interface with remarkable conversational competency and reasoning capabilities across many domains. However, since ChatGPT is trained with languages, it is not capable of processing or generating images from the visual world. Visual ChatGPT opens the door to investigating the visual roles of ChatGPT with the help of different Visual Foundation Models.
  arXiv  Detail & Related papers  (2023-03-08T15:50:02Z)
• Toolformer: Language Models Can Teach Themselves to Use Tools [62.04867424598204]
  Language models (LMs) exhibit remarkable abilities to solve new tasks from just a few examples or textual instructions, especially at scale. We show that LMs can teach themselves to use external tools via simple APIs and achieve the best of both worlds. We introduce Toolformer, a model trained to decide which APIs to call, when to call them, what arguments to pass, and how to best incorporate the results into future token prediction.
  arXiv  Detail & Related papers  (2023-02-09T16:49:57Z)
• FLAME: A small language model for spreadsheet formulas [25.667479554632735]
  We present FLAME, a transformer-based model trained exclusively on Excel formulas. We use sketch deduplication, introduce an Excel-specific formula tokenizer, and use domain-specific versions of masked span prediction. We evaluate FLAME on formula repair, formula completion, and similarity-based formula retrieval.
  arXiv  Detail & Related papers  (2023-01-31T17:29:43Z)
• TuringAdvice: A Generative and Dynamic Evaluation of Language Use [90.3029315711237]
  We propose TuringAdvice, a new challenge task and dataset for language understanding models. Given a written situation that a real person is currently facing, a model must generate helpful advice in natural language. Empirical results show that today's models struggle at TuringAdvice.
  arXiv  Detail & Related papers  (2020-04-07T18:00:03Z)
• A Structured Approach to the development of Solutions in Excel [0.0]
  This paper considers the use of controversial or lesser-used techniques to create a coherent solution strategy. The problem is solved by a sequence of formulas resembling the steps of a programmed language.
  arXiv  Detail & Related papers  (2017-04-04T18:22:26Z)

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.