An Interactive Visual Enhancement for Prompted Programmatic Weak Supervision in Text Classification

Simple item page
dc.contributor.authorLin, Yimingen_US
dc.contributor.authorWei, Shuqien_US
dc.contributor.authorZhang, Huijieen_US
dc.contributor.authorQu, Dezhanen_US
dc.contributor.authorBai, Jinghanen_US
dc.contributor.editorAigner, Wolfgangen_US
dc.contributor.editorAndrienko, Nataliaen_US
dc.contributor.editorWang, Beien_US
dc.date.accessioned2025-05-26T06:38:20Z
dc.date.available2025-05-26T06:38:20Z
dc.date.issued2025
dc.description.abstractProgrammatic Weak Supervision (PWS) has emerged as a powerful technique for text classification. By aggregating weak labels provided by manually written label functions, it allows training models on large-scale unlabeled data without the need for costly manual annotations. As an improvement, Prompted PWS incorporates pre-trained large language models (LLMs) as part of the label function, replacing programs coded by experts with natural language prompts. This allows for the more accessible expression of complex and ambiguous concepts. However, the existing workflow does not fully utilize the advantages of Prompted PWS, and the annotators have difficulty in effectively converging their ideas to develop high-quality LFs, and lack support during the iterations. To address this issue, this study improves the existing PWS workflow through interactive visualization. We first propose a collaborative LF development workflow between humans and LLMs, where the large language model assists humans in creating a structured development space for exploration and automatically generates prompted LFs based on human selections. Annotators can integrate their knowledge through informed selection and judgment. Then, we present an interactive visual system that supports efficient development, in-depth exploration, and iteration of LFs. Our evaluation, comprising a quantitative evaluation on the benchmark, a case study, and a user study, demonstrates the effectiveness of our approach.en_US
dc.description.sectionheadersAI-Enhanced Visualization
dc.description.seriesinformationComputer Graphics Forum
dc.identifier.doi10.1111/cgf.70131
dc.identifier.issn1467-8659
dc.identifier.pages11 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.70131
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70131
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Human-centered computing → Visual analytics; Information visualization
dc.subjectHuman centered computing → Visual analytics
dc.subjectInformation visualization
dc.titleAn Interactive Visual Enhancement for Prompted Programmatic Weak Supervision in Text Classificationen_US
Files
Original bundle
Now showing 1 - 3 of 3
Thumbnail Image
Name:
cgf70131.pdf
Size:
1.94 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
1186-file-i8.mp4
Size:
22.9 MB
Format:
Video MP4
Download
Thumbnail Image
Name:
1186-file-i9.pdf
Size:
2.14 MB
Format:
Adobe Portable Document Format
Download
Collections
44-Issue 3