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

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.

Recommended citation: Zhou, Y., Xing, Y., Borgo, R., & Abdul-Rahman, A. (2024). Visual Interpretation of Tagging: Advancing Understanding in Task-Oriented Dialogue Systems. In EG UK Computer Graphics & Visual Computing (2024). doi: 10.2312/cgvc20241236.
Paper | Bibtex