Raiven: LLM-Based Visualization Authoring via Domain-Specific Language Mediation

TL;DR

Raiven is a system that uses a domain-specific language and deterministic compilation to enable accurate, efficient, and verifiable visualization authoring with large language models, bridging scientific and information visualization.

Contribution

Raiven introduces a formally defined DSL and a deterministic compilation process, ensuring correctness and data integrity in LLM-based visualization authoring.

Findings

Raiven achieves 100% compilation success in 100 tasks.

Raiven is up to six times faster and cheaper than existing LLM approaches.

User study shows Raiven reduces debugging effort and improves visualization correctness.

Abstract

Visualization is central to scientific discovery, yet authoring tools remain split between information and scientific visualization, and expertise in one rarely transfers to the other. Large Language Model (LLM) based systems promise to bridge this gap through natural language, but current approaches generate code non-deterministically, with no guarantee of correctness and no protection against silent data fabrication. We present Raiven, a conversational system that mediates visualization authoring through a formally defined domain-specific language. RaivenDSL unifies scientific and information visualization in a single representation spanning 2D, 3D, and tabular data. The LLM produces a compact RaivenDSL specification under schema-guided constraints, and a deterministic compiler translates it to executable D3 or VTK.js code. Because the LLM operates only on dataset metadata, outputs are deterministic, specifications are verifiable before execution, and data fabrication is impossible by construction. In a 100-task benchmark, Raiven achieves 100% compilation, is up to six times faster and six times cheaper than state-of-the-art LLMs, while improving interaction quality, correctness, and data faithfulness. An expert user study shows that Raiven significantly reduces debugging effort and makes it easier to produce correct visualizations.