Chat2VIS: Generating Data Visualizations via Natural Language Using ChatGPT, Codex and GPT-3 Large Language Models

Simple item page
dc.citation.volume11
dc.contributor.authorMaddigan P
dc.contributor.authorSusnjak T
dc.contributor.editorDidimo W
dc.date.accessioned2024-10-10T18:33:55Z
dc.date.available2024-10-10T18:33:55Z
dc.date.issued2023-05-08
dc.description.abstractThe field of data visualisation has long aimed to devise solutions for generating visualisations directly from natural language text. Research in Natural Language Interfaces (NLIs) has contributed towards the development of such techniques. However, the implementation of workable NLIs has always been challenging due to the inherent ambiguity of natural language, as well as in consequence of unclear and poorly written user queries which pose problems for existing language models in discerning user intent. Instead of pursuing the usual path of developing new iterations of language models, this study uniquely proposes leveraging the advancements in pre-trained large language models (LLMs) such as ChatGPT and GPT-3 to convert free-form natural language directly into code for appropriate visualisations. This paper presents a novel system, Chat2VIS, which takes advantage of the capabilities of LLMs and demonstrates how, with effective prompt engineering, the complex problem of language understanding can be solved more efficiently, resulting in simpler and more accurate end-to-end solutions than prior approaches. Chat2VIS shows that LLMs together with the proposed prompts offer a reliable approach to rendering visualisations from natural language queries, even when queries are highly misspecified and underspecified. This solution also presents a significant reduction in costs for the development of NLI systems, while attaining greater visualisation inference abilities compared to traditional NLP approaches that use hand-crafted grammar rules and tailored models. This study also presents how LLM prompts can be constructed in a way that preserves data security and privacy while being generalisable to different datasets. This work compares the performance of GPT-3, Codex and ChatGPT across several case studies and contrasts the performances with prior studies.
dc.description.confidentialfalse
dc.edition.edition2023
dc.format.pagination45181-45193
dc.identifier.citationMaddigan P, Susnjak T. (2023). Chat2VIS: Generating Data Visualizations via Natural Language Using ChatGPT, Codex and GPT-3 Large Language Models. IEEE Access. 11. (pp. 45181-45193).
dc.identifier.doi10.1109/ACCESS.2023.3274199
dc.identifier.eissn2169-3536
dc.identifier.elements-typejournal-article
dc.identifier.urihttps://mro.massey.ac.nz/handle/10179/71677
dc.languageEnglish
dc.publisherIEEE
dc.publisher.urihttps://ieeexplore.ieee.org/document/10121440
dc.relation.isPartOfIEEE Access
dc.rights(c) 2023 The Author/s
dc.rightsCC BY-NC-ND 4.0
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectChatGPT
dc.subjectcodex
dc.subjectend-to-end visualisations from natural language
dc.subjectGPT-3
dc.subjectlarge language models
dc.subjectnatural language interfaces
dc.subjecttext-to-visualisation
dc.titleChat2VIS: Generating Data Visualizations via Natural Language Using ChatGPT, Codex and GPT-3 Large Language Models
dc.typeJournal article
pubs.elements-id461873
pubs.organisational-groupOther
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Published version.pdf
Size:
3.63 MB
Format:
Adobe Portable Document Format
Description:
461873 PDF.pdf
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
9.22 KB
Format:
Plain Text
Description:
Download
Collections
Journal Articles