Leveraging Large Language Models to Enhance Domain Expert Inclusion in Data Science Workflows
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929334857498624 |
|---|---|
| author | Shih, Jasmine Y. Mohanty, Vishal Katsis, Yannis Subramonyam, Hariharan |
| author_facet | Shih, Jasmine Y. Mohanty, Vishal Katsis, Yannis Subramonyam, Hariharan |
| contents | Domain experts can play a crucial role in guiding data scientists to optimize machine learning models while ensuring contextual relevance for downstream use. However, in current workflows, such collaboration is challenging due to differing expertise, abstract documentation practices, and lack of access and visibility into low-level implementation artifacts. To address these challenges and enable domain expert participation, we introduce CellSync, a collaboration framework comprising (1) a Jupyter Notebook extension that continuously tracks changes to dataframes and model metrics and (2) a Large Language Model powered visualization dashboard that makes those changes interpretable to domain experts. Through CellSync's cell-level dataset visualization with code summaries, domain experts can interactively examine how individual data and modeling operations impact different data segments. The chat features enable data-centric conversations and targeted feedback to data scientists. Our preliminary evaluation shows that CellSync provides transparency and promotes critical discussions about the intents and implications of data operations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_02260 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Leveraging Large Language Models to Enhance Domain Expert Inclusion in Data Science Workflows Shih, Jasmine Y. Mohanty, Vishal Katsis, Yannis Subramonyam, Hariharan Human-Computer Interaction Domain experts can play a crucial role in guiding data scientists to optimize machine learning models while ensuring contextual relevance for downstream use. However, in current workflows, such collaboration is challenging due to differing expertise, abstract documentation practices, and lack of access and visibility into low-level implementation artifacts. To address these challenges and enable domain expert participation, we introduce CellSync, a collaboration framework comprising (1) a Jupyter Notebook extension that continuously tracks changes to dataframes and model metrics and (2) a Large Language Model powered visualization dashboard that makes those changes interpretable to domain experts. Through CellSync's cell-level dataset visualization with code summaries, domain experts can interactively examine how individual data and modeling operations impact different data segments. The chat features enable data-centric conversations and targeted feedback to data scientists. Our preliminary evaluation shows that CellSync provides transparency and promotes critical discussions about the intents and implications of data operations. |
| title | Leveraging Large Language Models to Enhance Domain Expert Inclusion in Data Science Workflows |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2405.02260 |