On Pre-training of Multimodal Language Models Customized for Chart Understanding

• URL: http://arxiv.org/abs/2407.14506v2
• Date: Wed, 31 Jul 2024 21:01:16 GMT
• Title: On Pre-training of Multimodal Language Models Customized for Chart Understanding
• Authors: Wan-Cyuan Fan, Yen-Chun Chen, Mengchen Liu, Lu Yuan, Leonid Sigal,
• Abstract summary: This paper explores the training processes necessary to improve MLLMs' comprehension of charts. We introduce CHOPINLLM, an MLLM tailored for in-depth chart comprehension.
• Score: 83.99377088129282
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent studies customizing Multimodal Large Language Models (MLLMs) for domain-specific tasks have yielded promising results, especially in the field of scientific chart comprehension. These studies generally utilize visual instruction tuning with specialized datasets to enhance question and answer (QA) accuracy within the chart domain. However, they often neglect the fundamental discrepancy between natural image-caption pre-training data and digital chart image-QA data, particularly in the models' capacity to extract underlying numeric values from charts. This paper tackles this oversight by exploring the training processes necessary to improve MLLMs' comprehension of charts. We present three key findings: (1) Incorporating raw data values in alignment pre-training markedly improves comprehension of chart data. (2) Replacing images with their textual representation randomly during end-to-end fine-tuning transfer the language reasoning capability to chart interpretation skills. (3) Requiring the model to first extract the underlying chart data and then answer the question in the fine-tuning can further improve the accuracy. Consequently, we introduce CHOPINLLM, an MLLM tailored for in-depth chart comprehension. CHOPINLLM effectively interprets various types of charts, including unannotated ones, while maintaining robust reasoning abilities. Furthermore, we establish a new benchmark to evaluate MLLMs' understanding of different chart types across various comprehension levels. Experimental results show that CHOPINLLM exhibits strong performance in understanding both annotated and unannotated charts across a wide range of types.

Related papers

• RealCQA-V2 : Visual Premise Proving A Manual COT Dataset for Charts [2.9201864249313383]
  We introduce Visual Premise Proving, a novel task tailored to refine the process of chart question answering. This approach represents a departure from conventional accuracy-based evaluation methods. A model adept at reasoning is expected to demonstrate proficiency in both data retrieval and the structural understanding of charts.
  arXiv  Detail & Related papers  (2024-10-29T19:32:53Z)
• Distill Visual Chart Reasoning Ability from LLMs to MLLMs [38.62832112530892]
  Solving complex chart Q&A tasks requires advanced visual reasoning abilities in multimodal large language models (MLLMs) We propose Code-as-Intermediary Translation (CIT), a cost-effective, efficient and easily scalable data synthesis method for distilling visual reasoning abilities from LLMs to MLLMs. We employ text-based synthesizing techniques to construct chart-plotting code and produce ReachQA, a dataset containing 3k reasoning-intensive charts and 20k Q&A pairs.
  arXiv  Detail & Related papers  (2024-10-24T14:50:42Z)
• AltChart: Enhancing VLM-based Chart Summarization Through Multi-Pretext Tasks [31.414783623207477]
  We introduce the AltChart dataset, comprising 10,000 real chart images, each paired with a comprehensive summary. We propose a new method for pretraining Vision-Language Models (VLMs) to learn fine-grained chart representations. We conduct extensive evaluations of four leading chart summarization models, analyzing how accessible their descriptions are.
  arXiv  Detail & Related papers  (2024-05-22T12:18:52Z)
• TinyChart: Efficient Chart Understanding with Visual Token Merging and Program-of-Thoughts Learning [83.58521787193293]
  We present TinyChart, an efficient MLLM for chart understanding with only 3B parameters. TinyChart overcomes two key challenges in efficient chart understanding: (1) reduce the burden of learning numerical computations through a Program-of-Thoughts (PoT) learning strategy, and (2) reduce lengthy vision feature sequences produced by the vision transformer for high-resolution images through a Vision Token Merging module.
  arXiv  Detail & Related papers  (2024-04-25T14:23:24Z)
• ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning [54.89249749894061]
  ChartAssistant is a vision-language model for universal chart comprehension and reasoning. It undergoes a two-stage training process, starting with pre-training on chart-to-table parsing to align chart and text. Experimental results demonstrate significant performance gains over the state-of-the-art UniChart and Chartllama method.
  arXiv  Detail & Related papers  (2024-01-04T17:51:48Z)
• ChartLlama: A Multimodal LLM for Chart Understanding and Generation [70.1393163657813]
  We create a high-quality instruction-tuning dataset leveraging GPT-4. Next, we introduce ChartLlama, a multi-modal large language model that we've trained using our created dataset.
  arXiv  Detail & Related papers  (2023-11-27T15:20:23Z)
• StructChart: Perception, Structuring, Reasoning for Visual Chart Understanding [58.38480335579541]
  Current chart-related tasks focus on either chart perception which refers to extracting information from the visual charts, or performing reasoning given the extracted data. In this paper, we aim to establish a unified and label-efficient learning paradigm for joint perception and reasoning tasks. Experiments are conducted on various chart-related tasks, demonstrating the effectiveness and promising potential for a unified chart perception-reasoning paradigm.
  arXiv  Detail & Related papers  (2023-09-20T12:51:13Z)
• Enhanced Chart Understanding in Vision and Language Task via Cross-modal Pre-training on Plot Table Pairs [71.55796212450055]
  We introduce ChartT5, a V+L model that learns how to interpret table information from chart images via cross-modal pre-training on plot table pairs. Specifically, we propose two novel pre-training objectives: Masked Header Prediction (MHP) and Masked Value Prediction (MVP)
  arXiv  Detail & Related papers  (2023-05-29T22:29:03Z)
• UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning [29.947053208614246]
  We present UniChart, a pretrained model for chart comprehension and reasoning. UniChart encodes the relevant text, data, and visual elements of charts and then uses a chart-grounded text decoder to generate the expected output in natural language. We propose several chart-specific pretraining tasks that include: (i) low-level tasks to extract the visual elements (e.g., bars, lines) and data from charts, and (ii) high-level tasks to acquire chart understanding and reasoning skills.
  arXiv  Detail & Related papers  (2023-05-24T06:11:17Z)
• Chart-to-Text: A Large-Scale Benchmark for Chart Summarization [9.647079534077472]
  We present Chart-to-text, a large-scale benchmark with two datasets and a total of 44,096 charts. We explain the dataset construction process and analyze the datasets.
  arXiv  Detail & Related papers  (2022-03-12T17:01:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.