CycleChart: A Unified Consistency-Based Learning Framework for Bidirectional Chart Understanding and Generation
This work addresses the lack of shared semantics in chart-related tasks, offering a step toward more general chart understanding models, though it is incremental in integrating existing tasks.
The authors tackled the problem of isolated chart-specific tasks by introducing CycleChart, a unified framework for bidirectional chart understanding and generation, which achieved strong results across chart generation, parsing, and question answering tasks.
Current chart-specific tasks, such as chart question answering, chart parsing, and chart generation, are typically studied in isolation, preventing models from learning the shared semantics that link chart generation and interpretation. We introduce CycleChart, a consistency-based learning framework for bidirectional chart understanding and generation. CycleChart adopts a schema-centric formulation as a common interface across tasks. We construct a consistent multi-task dataset, where each chart sample includes aligned annotations for schema prediction, data parsing, and question answering. To learn cross-directional chart semantics, CycleChart introduces a generate-parse consistency objective: the model generates a chart schema from a table and a textual query, then learns to recover the schema and data from the generated chart, enforcing semantic alignment across directions. CycleChart achieves strong results on chart generation, chart parsing, and chart question answering, demonstrating improved cross-task generalization and marking a step toward more general chart understanding models.