Prompt Lenses: Improving the Magic of Lenses (for Text Analysis)

Simple item page
dc.contributor.authorSatkunarajan, Jenaen_US
dc.contributor.authorWohlfart, Phillipen_US
dc.contributor.authorBeck, Samuelen_US
dc.contributor.authorFranke, Maxen_US
dc.contributor.authorKoch, Steffenen_US
dc.contributor.editorEl-Assady, Mennatallahen_US
dc.contributor.editorOttley, Alvittaen_US
dc.contributor.editorTominski, Christianen_US
dc.date.accessioned2025-05-26T06:58:53Z
dc.date.available2025-05-26T06:58:53Z
dc.date.issued2025
dc.description.abstractIncorporating the analytical power of LLMs with the fast-paced interaction of magic lens-based exploration is an intriguing prospect. Unfortunately, the costs of LLM-generated analyses are high, and applying them continuously seems prohibitive at the moment. Accordingly, we suggest an LLM integration into magic lenses that supports the progressive triggering of costly analyses based on users' interest in the data hovered with the lens. We exemplify this approach with a lens technique for exploring dimensionality-reduced embeddings of visualization paper abstracts shown in a scatterplot. Our proposed approach links back analysis results to the explored visualization improving the comprehensibility and the assessment of the shown results.en_US
dc.description.sectionheadersSystems and Applications
dc.description.seriesinformationEuroVis 2025 - Short Papers
dc.identifier.doi10.2312/evs.20251086
dc.identifier.isbn978-3-03868-282-0
dc.identifier.pages5 pages
dc.identifier.urihttps://doi.org/10.2312/evs.20251086
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/evs20251086
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Human-centered computing → Visual analytics
dc.subjectHuman centered computing → Visual analytics
dc.titlePrompt Lenses: Improving the Magic of Lenses (for Text Analysis)en_US
Files
Original bundle
Now showing 1 - 3 of 3
No Thumbnail Available
Name:
evs20251086.pdf
Size:
2.67 MB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
1038-file-i7.pdf
Size:
5.58 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
1038-file-i8.mov
Size:
88.73 MB
Format:
Video Quicktime
Download
Collections
EuroVisShort2025