# C2: Scalable Auto-Feedback for LLM-based Chart Generation

arXiv: https://arxiv.org/abs/2410.18652 · HTML: https://mlsanity.com/paper/2410.18652/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 80 references that are in the map.
- First posted on arXiv 24 Oct 2024.

## Builds on (most cited first, 30 of 33)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://mlsanity.com/paper/2309.10691/) (2023)
- [ChartBench: A Benchmark for Complex Visual Reasoning in Charts](https://mlsanity.com/paper/2312.15915/) (2023)
- [MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization](https://mlsanity.com/paper/2402.11453/) (2024)
- [Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning](https://mlsanity.com/paper/2406.14283/) (2024)
- [NL4DV: A Toolkit for Generating Analytic Specifications for Data Visualization from Natural Language Queries](https://mlsanity.com/paper/2008.10723/) (2020)
- [EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteria](https://mlsanity.com/paper/2309.13633/) (2023)
- [ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural Language](https://mlsanity.com/paper/2311.01920/) (2023)
- [Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback](https://mlsanity.com/paper/2403.16792/) (2024)
- [LiteSearch: Efficacious Tree Search for LLM](https://mlsanity.com/paper/2407.00320/) (2024)
- [Striking a Balance: Reader Takeaways and Preferences when Integrating Text and Charts](https://mlsanity.com/paper/2208.01780/) (2022)
- [Text2Chart31: Instruction Tuning for Chart Generation with Automatic Feedback](https://mlsanity.com/paper/2410.04064/) (2024)
- [Towards Understanding How Readers Integrate Charts and Captions: A Case Study with Line Charts](https://mlsanity.com/paper/2101.08235/) (2021)
- [ChartStory: Automated Partitioning, Layout, and Captioning of Charts into Comic-Style Narratives](https://mlsanity.com/paper/2103.03996/) (2021)
- [Challenges and Opportunities in Data Visualization Education: A Call to Action](https://mlsanity.com/paper/2308.07703/) (2023)
- [Understanding Data Visualization Design Practice](https://mlsanity.com/paper/2108.07855/) (2021)
- [Parameterizing Context: Unleashing the Power of Parameter-Efficient Fine-Tuning and In-Context Tuning for Continual Table Semantic Parsing](https://mlsanity.com/paper/2310.04801/) (2023)

## Built on by (most cited first, 6 of 6)

- [Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion](https://mlsanity.com/paper/2511.18734/) (2025)
- [StyleTailor: Towards Personalized Fashion Styling via Hierarchical Negative Feedback](https://mlsanity.com/paper/2508.06555/) (2025)
- [Does It Run and Is That Enough? Revisiting Text-to-Chart Generation with a Multi-Agent Approach](https://mlsanity.com/paper/2506.06175/) (2025)
- [PRISM: A Benchmark for Programmatic Spatial-Temporal Reasoning](https://mlsanity.com/paper/2605.19382/) (2026)
- [ChartAnno: Benchmarking Multimodal Large Language Models for Chart Annotation Generation](https://mlsanity.com/paper/2608.03464/) (2026)
- [DEEPCHART: How Far are LLMs from Faithful Data-Science Chart Generation?](https://mlsanity.com/paper/2608.26757/) (2026)

## Abstract (arXiv)

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 instruction, data, 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, C2, 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 chartsquared.github.io, with ample qualitative examples.