Visual Interpretation of Tagging: Advancing Understanding in Task-Oriented Dialogue Systems
| dc.contributor.author | Zhou, Yazhuo | en_US |
| dc.contributor.author | Xing, Yiwen | en_US |
| dc.contributor.author | Abdul-Rahman, Alfie | en_US |
| dc.contributor.author | Borgo, Rita | en_US |
| dc.contributor.editor | Hunter, David | en_US |
| dc.contributor.editor | Slingsby, Aidan | en_US |
| dc.date.accessioned | 2024-09-09T05:45:34Z | |
| dc.date.available | 2024-09-09T05:45:34Z | |
| dc.date.issued | 2024 | |
| dc.description.abstract | In 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.sectionheaders | Machine Learning and LLM-enabled Visual Analytics | |
| dc.description.seriesinformation | Computer Graphics and Visual Computing (CGVC) | |
| dc.identifier.doi | 10.2312/cgvc.20241236 | |
| dc.identifier.isbn | 978-3-03868-249-3 | |
| dc.identifier.pages | 9 pages | |
| dc.identifier.uri | https://doi.org/10.2312/cgvc.20241236 | |
| dc.identifier.uri | https://diglib.eg.org/handle/10.2312/cgvc20241236 | |
| dc.publisher | The Eurographics Association | en_US |
| dc.rights | Attribution 4.0 International License | |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
| dc.subject | CCS Concepts: Human-centered computing → Visual analytics | |
| dc.subject | Human centered computing → Visual analytics | |
| dc.title | Visual Interpretation of Tagging: Advancing Understanding in Task-Oriented Dialogue Systems | en_US |
Files
Original bundle
1 - 1 of 1