$C^2$: Scalable Auto-Feedback for LLM-based Chart Generation

View a PDF of the paper titled $C^2$: Scalable Auto-Feedback for LLM-based Chart Generation, by Woosung Koh and 9 other authors

View PDF

Abstract:Generating high-quality charts with Large Language Models (LLMs) presents significant challenges due to limited data and the high cost of scaling through human curation. $langle text{instruction}, text{data}, text{code} rangle$ triplets are scarce and expensive to manually curate as their creation demands technical expertise. To address this scalability challenge, we introduce a reference-free automatic feedback generator, which eliminates the need for costly human intervention. Our novel framework, C$^2$, consists of (1) an automatic feedback provider (ChartAF) and (2) a diverse, reference-free dataset (ChartUIE-8K). The results are compelling: in our first experiment, 74% of respondents strongly preferred, and 10% preferred, the results after feedback. The second post-feedback experiment demonstrates that ChartAF outperform nine baselines. Moreover, ChartUIE-8K significantly improves data diversity by increasing queries, datasets, and chart types by 5982%, 1936%, and 91%, respectively, over benchmarks. Finally, a study of LLM users revealed that 94% of participants preferred ChartUIE-8K’s queries, with 93% deeming them aligned with real-world use cases. Core contributions are available as open-source at this http URL, with ample qualitative examples.