VegaChat: A Robust Framework for LLM-Based Chart Generation and Assessment
This addresses the problem of inconsistent assessment and comparison in chart generation for researchers and practitioners, though it is incremental as it builds on existing NL2VIS methods.
The paper tackles the lack of standardized evaluation metrics and underspecified natural language in NL2VIS systems by introducing VegaChat, a framework with Spec Score and Vision Score metrics, achieving near-zero invalid visualizations and strong correlation with human judgments (Pearson 0.65 and 0.71).
Natural-language-to-visualization (NL2VIS) systems based on large language models (LLMs) have substantially improved the accessibility of data visualization. However, their further adoption is hindered by two coupled challenges: (i) the absence of standardized evaluation metrics makes it difficult to assess progress in the field and compare different approaches; and (ii) natural language descriptions are inherently underspecified, so multiple visualizations may be valid for the same query. To address these issues, we introduce VegaChat, a framework for generating, validating, and assessing declarative visualizations from natural language. We propose two complementary metrics: Spec Score, a deterministic metric that measures specification-level similarity without invoking an LLM, and Vision Score, a library-agnostic, image-based metric that leverages a multimodal LLM to assess chart similarity and prompt compliance. We evaluate VegaChat on the NLV Corpus and on the annotated subset of ChartLLM. VegaChat achieves near-zero rates of invalid or empty visualizations, while Spec Score and Vision Score exhibit strong correlation with human judgments (Pearson 0.65 and 0.71, respectively), indicating that the proposed metrics support consistent, cross-library comparison. The code and evaluation artifacts are available at https://zenodo.org/records/17062309.