# Advancing Multimodal Large Language Models in Chart Question Answering with Visualization-Referenced Instruction Tuning

arXiv: https://arxiv.org/abs/2407.20174 · HTML: https://mlsanity.com/paper/2407.20174/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 57 of its 74 references that are in the map.
- First posted on arXiv 29 Jul 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Chart understanding and anomaly detection](https://mlsanity.com/mllm/chart-understanding-and-anomaly-detection/)

## Builds on (most cited first, 30 of 57)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge](https://mlsanity.com/paper/2206.01718/) (2022)
- [OCR-free Document Understanding Transformer](https://mlsanity.com/paper/2111.15664/) (2021)
- [Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding](https://mlsanity.com/paper/2210.03347/) (2022)
- [PlotQA: Reasoning over Scientific Plots](https://mlsanity.com/paper/1909.00997/) (2019)
- [SemDeDup: Data-efficient learning at web-scale through semantic deduplication](https://mlsanity.com/paper/2303.09540/) (2023)
- [GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest](https://mlsanity.com/paper/2307.03601/) (2023)
- [Honeybee: Locality-enhanced Projector for Multimodal LLM](https://mlsanity.com/paper/2312.06742/) (2023)
- [Chart-to-Text: A Large-Scale Benchmark for Chart Summarization](https://mlsanity.com/paper/2203.06486/) (2022)
- [ChartLlama: A Multimodal LLM for Chart Understanding and Generation](https://mlsanity.com/paper/2311.16483/) (2023)
- [DePlot: One-shot visual language reasoning by plot-to-table translation](https://mlsanity.com/paper/2212.10505/) (2022)

## Built on by (most cited first, 27 of 27)

- [Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey](https://mlsanity.com/paper/2411.17558/) (2024)
- [Distill Visual Chart Reasoning Ability from LLMs to MLLMs](https://mlsanity.com/paper/2410.18798/) (2024)
- [LightVA: Lightweight Visual Analytics with LLM Agent-Based Task Planning and Execution](https://mlsanity.com/paper/2411.05651/) (2024)
- [Effective Training Data Synthesis for Improving MLLM Chart Understanding](https://mlsanity.com/paper/2508.06492/) (2025)
- [Unmasking Deceptive Visuals: Benchmarking Multimodal Large Language Models on Misleading Chart Question Answering](https://mlsanity.com/paper/2503.18172/) (2025)
- [VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models](https://mlsanity.com/paper/2508.09945/) (2025)
- [InterChat: Enhancing Generative Visual Analytics using Multimodal Interactions](https://mlsanity.com/paper/2503.04110/) (2025)
- [EncQA: Benchmarking Vision-Language Models on Visual Encodings for Charts](https://mlsanity.com/paper/2508.04650/) (2025)
- [The Confidence Paradox: Can LLM Know When It's Wrong](https://mlsanity.com/paper/2506.23464/) (2025)
- [RAC3: Retrieval-Augmented Corner Case Comprehension for Autonomous Driving with Vision-Language Models](https://mlsanity.com/paper/2412.11050/) (2024)
- [Protecting multimodal large language models against misleading visualizations](https://mlsanity.com/paper/2502.20503/) (2025)
- [See or Recall: A Sanity Check for the Role of Vision in Solving Visualization Question Answer Tasks with Multimodal LLMs](https://mlsanity.com/paper/2504.09809/) (2025)
- [ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question Answering](https://mlsanity.com/paper/2505.23242/) (2025)
- [ChartCap: Mitigating Hallucination of Dense Chart Captioning](https://mlsanity.com/paper/2508.03164/) (2025)
- [Exploring Multimodal Prompt for Visualization Authoring with Large Language Models](https://mlsanity.com/paper/2504.13700/) (2025)
- [CHART-6: Human-Centered Evaluation of Data Visualization Understanding in Vision-Language Models](https://mlsanity.com/paper/2505.17202/) (2025)
- [VizDefender: Unmasking Visualization Tampering through Proactive Localization and Intent Inference](https://mlsanity.com/paper/2512.18853/) (2025)
- [MultiVis-Agent: A Multi-Agent Framework with Logic Rules for Reliable and Comprehensive Cross-Modal Data Visualization](https://mlsanity.com/paper/2601.18320/) (2026)
- [Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training Framework](https://mlsanity.com/paper/2606.29808/) (2026)
- [Evaluating Graphical Perception with Multimodal LLMs](https://mlsanity.com/paper/2504.04221/) (2025)
- [Benchmarking Multimodal LLMs on Code Generation for Complex Interactive Webpages](https://mlsanity.com/paper/2606.00154/) (2026)
- [Benchmark It Yourself (BIY): Preparing a Dataset and Benchmarking AI Models for Scatterplot-Related Tasks](https://mlsanity.com/paper/2510.06071/) (2025)
- [SVG Decomposition for Enhancing Large Multimodal Models Visualization Comprehension: A Study with Floor Plans](https://mlsanity.com/paper/2511.03478/) (2025)
- [ChartAttack: Testing the Vulnerability of LLMs to Malicious Prompting in Chart Generation](https://mlsanity.com/paper/2601.12983/) (2026)
- [REChart: Reasoning-Efficient Chart Editing with Large Reasoning Models](https://mlsanity.com/paper/2608.17414/) (2026)
- [LegendBench: A Diagnostic Benchmark for Legend Understanding with Counterfactual Interventions](https://mlsanity.com/paper/2609.24172/) (2026)
- [Where LLMs Fail with Visualization DSLs](https://mlsanity.com/paper/2610.01873/) (2026)

## Abstract (arXiv)

Emerging multimodal large language models (MLLMs) exhibit great potential for chart question answering (CQA). Recent efforts primarily focus on scaling up training datasets (i.e., charts, data tables, and question-answer (QA) pairs) through data collection and synthesis. However, our empirical study on existing MLLMs and CQA datasets reveals notable gaps. First, current data collection and synthesis focus on data volume and lack consideration of fine-grained visual encodings and QA tasks, resulting in unbalanced data distribution divergent from practical CQA scenarios. Second, existing work follows the training recipe of the base MLLMs initially designed for natural images, under-exploring the adaptation to unique chart characteristics, such as rich text elements. To fill the gap, we propose a visualization-referenced instruction tuning approach to guide the training dataset enhancement and model development. Specifically, we propose a novel data engine to effectively filter diverse and high-quality data from existing datasets and subsequently refine and augment the data using LLM-based generation techniques to better align with practical QA tasks and visual encodings. Then, to facilitate the adaptation to chart characteristics, we utilize the enriched data to train an MLLM by unfreezing the vision encoder and incorporating a mixture-of-resolution adaptation strategy for enhanced fine-grained recognition. Experimental results validate the effectiveness of our approach. Even with fewer training examples, our model consistently outperforms state-of-the-art CQA models on established benchmarks. We also contribute a dataset split as a benchmark for future research. Source codes and datasets of this paper are available at https://github.com/zengxingchen/ChartQA-MLLM.