---
license: gpl-3.0
language:
- en
---

# ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning

Venue: **ACL 2024 (Findings)**

Paper Link: https://arxiv.org/abs/2403.09028 

The abstract of the paper states that: 
> Charts provide visual representations of data and are widely used for analyzing information, addressing queries, and conveying insights to others. Various chart-related downstream tasks have emerged recently, such as question-answering and summarization. A common strategy to solve these tasks is to fine-tune various models originally trained on vision tasks language. However, such task-specific models are not capable of solving a wide range of chart-related tasks, constraining their real-world applicability. To overcome these challenges, we introduce ChartInstruct: a novel chart-specific vision-language Instruction following dataset comprising 191K instructions generated with 71K charts. We then present two distinct systems for instruction tuning on such datasets: (1) an end-to-end model that connects a vision encoder for chart understanding with a LLM; and (2) a pipeline model that employs a two-step approach to extract chart data tables and input them into the LLM. In experiments on four downstream tasks, we first show the effectiveness of our model--achieving a new set of state-of-the-art results. Further evaluation shows that our instruction-tuning approach supports a wide array of real-world chart comprehension and reasoning scenarios, thereby expanding the scope and applicability of our models to new kinds of tasks.
# Web Demo
If you wish to quickly try our model, you can access our public web demo hosted on the Hugging Face Spaces platform with a friendly interface!

[ChartInstruct-Llama2 Web Demo](https://huggingface.co/spaces/ahmed-masry/ChartInstruct-LLama2)

# Inference
You can easily use our models for inference with the huggingface library! 
You just need to do the following:
1. Chage the **_image_path_** to your chart example image path on your system
2. Write the **_input_text_** 

We recommend using beam search with a beam size of 4, but if your machine has low memory, you can remove the num_beams from the generate method. 
```
from PIL import Image
import requests
from transformers import AutoProcessor, LlavaForConditionalGeneration
import torch

torch.hub.download_url_to_file('https://raw.githubusercontent.com/vis-nlp/ChartQA/main/ChartQA%20Dataset/val/png/multi_col_1229.png', 'chart_example_1.png')

image_path = "/content/chart_example_1.png"
input_text = "What is the share of respondants who prefer Whatsapp in the 18-29 age group?"

input_prompt = f"<image>\n Question: {input_text} Answer: "

model = LlavaForConditionalGeneration.from_pretrained("ahmed-masry/ChartInstruct-LLama2", torch_dtype=torch.float16)
processor = AutoProcessor.from_pretrained("ahmed-masry/ChartInstruct-LLama2")


image = Image.open(image_path).convert('RGB')

inputs = processor(text=prompt, images=image, return_tensors="pt")
inputs = {k: v.to(device) for k, v in inputs.items()}

# change type if pixel_values in inputs to fp16. 
inputs['pixel_values'] = inputs['pixel_values'].to(torch.float16)
prompt_length = inputs['input_ids'].shape[1]

# Generate
generate_ids = model.generate(**inputs, num_beams=4, max_new_tokens=512)
output_text = processor.batch_decode(generate_ids[:, prompt_length:], skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
print(output_text)

```

# Contact
If you have any questions about this work, please contact **[Ahmed Masry](https://ahmedmasryku.github.io/)** using the following email addresses: **amasry17@ku.edu.tr** or **ahmed.elmasry24653@gmail.com**.

# Reference
Please cite our paper if you use our model in your research. 

```
@misc{masry2024chartinstruct,
      title={ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning}, 
      author={Ahmed Masry and Mehrad Shahmohammadi and Md Rizwan Parvez and Enamul Hoque and Shafiq Joty},
      year={2024},
      eprint={2403.09028},
      archivePrefix={arXiv},
      primaryClass={id='cs.CL' full_name='Computation and Language' is_active=True alt_name='cmp-lg' in_archive='cs' is_general=False description='Covers natural language processing. Roughly includes material in ACM Subject Class I.2.7. Note that work on artificial languages (programming languages, logics, formal systems) that does not explicitly address natural-language issues broadly construed (natural-language processing, computational linguistics, speech, text retrieval, etc.) is not appropriate for this area.'}
}
```