RAGE-Vis:A Relation-Aware Generative Editing Interface for Natural Language-Based Chart Editing

2026-08-11

AI Summary

Existing natural language–driven chart editing approaches struggle to interpret complex, cross-component editing intents, often resulting in global inconsistencies. This work proposes a relation-aware generative editing interface that reverse-engineers bitmap charts into a parametric intermediate representation, explicitly modeling three types of relationships: visual encoding, structural layout, and expressive consistency. By automatically identifying and synchronizing potentially affected fields, the system effectively disambiguates vague or high-level natural language instructions and generates a hierarchical editing panel that enables users to jointly control both global and local parameters. Case studies and user evaluations demonstrate that this approach significantly improves editing efficiency and cross-component consistency in complex tasks such as style adjustment, data expansion, and legend layout.

Abstract

Natural language offers an easy way for users to express chart editing intents, which are often composite and cross-component (e.g., adjusting style, extending categories, highlighting values). However, existing methods typically map instructions to a single operation or widget, limiting their ability to handle high-level requests and often producing locally plausible but globally inconsistent results due to a lack of awareness of relationships between chart components. To address these challenges, we introduce RAGE-Vis, a Relation-Aware Generative Editing interface for natural language-based chart editing. The system supports bitmap chart images as input and converts them into an editable parameterized intermediate representation. Instead of mapping instructions to a single edit or widget, RAGE-Vis parses composite intents, identifies targets and scopes, and generates hierarchical editing panels for underspecified requests, enabling users to adjust both global settings and local parameters. Furthermore, RAGE-Vis identifies potentially affected fields based on visual encoding relations, structural relationships, and expressive consistency relations, and organizes them into actionable widgets to support cross-component coordinated controls. Through two case studies, we demonstrate the applicability of RAGE-Vis in complex editing tasks, including style adjustment, data extension, order rearrangement, legend layout, and color mapping. A user study further shows that participants can effectively handle underspecified requests, explore candidate alternatives, and maintain cross-component consistency with RAGE-Vis.

Problem

• natural language-based chart editing
• composite intents
• cross-component consistency
• relation-aware editing
• underspecified requests

Innovation

• relation-aware editing
• natural language interface
• chart generation
• cross-component consistency
• parameterized representation