Visual Interpretation of Tagging: Advancing Understanding in Task-Oriented Dialogue Systems

Simple item page
dc.contributor.authorZhou, Yazhuoen_US
dc.contributor.authorXing, Yiwenen_US
dc.contributor.authorAbdul-Rahman, Alfieen_US
dc.contributor.authorBorgo, Ritaen_US
dc.contributor.editorHunter, Daviden_US
dc.contributor.editorSlingsby, Aidanen_US
dc.date.accessioned2024-09-09T05:45:34Z
dc.date.available2024-09-09T05:45:34Z
dc.date.issued2024
dc.description.abstractIn task-oriented dialogue systems, tagging tasks leverage Large Language Models (LLMs) to understand dialogue semantics. The specifics of how these models capture and utilize dialogue semantics for decision-making remain unclear. Unlike binary or multi-classification, tagging involves complex multi-to-multi relationships between features and predictions, complicating attribution analyses. To address these challenges, we introduce a novel interactive visualization system that enhances understanding of dialogue semantics through attribution analysis. Our system offers a multi-level and layer-wise visualization framework, revealing the evolution of attributions across layers and allowing users to interactively probe attributions. With a dual-view for streamlined comparisons, users can effectively compare different LLMs. We demonstrate our system's effectiveness with a common task-oriented dialogue task: slot filling. This tool aids NLP experts in understanding attributions, diagnosing models, and advancing dialogue understanding development by identifying potential sources of model hallucinations.en_US
dc.description.sectionheadersMachine Learning and LLM-enabled Visual Analytics
dc.description.seriesinformationComputer Graphics and Visual Computing (CGVC)
dc.identifier.doi10.2312/cgvc.20241236
dc.identifier.isbn978-3-03868-249-3
dc.identifier.pages9 pages
dc.identifier.urihttps://doi.org/10.2312/cgvc.20241236
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/cgvc20241236
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.titleVisual Interpretation of Tagging: Advancing Understanding in Task-Oriented Dialogue Systemsen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
cgvc20241236.pdf
Size:
2.13 MB
Format:
Adobe Portable Document Format
Download
Collections
Computer Graphics & Visual Computing (CGVC) 2024