REVIEW 1 cited by
ChatGPT and Excel -- trust, but verify
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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.
Forward citations
Cited by 1 Pith paper
-
Large Language Models for Spreadsheets: Benchmarking Progress and Evaluating Performance with FLARE
FLARE, a new spreadsheet benchmark, shows that 20 LLMs do well on simple formulas but frequently fail on multi-step, logic-heavy spreadsheet tasks.
Discussion (0). Continue with ORCID to comment.