Skip to content

Alab-NII/tables-vs-charts

Repository files navigation

Format Matters: Tables vs. Charts

This is the repository for the paper: Format Matters: The Robustness of Multimodal LLMs in Reviewing Evidence from Tables and Charts (AAAI 2026)

Reproduction of Results

Table 2:

Edit base_path in Line 49 to obtain all results in Table 2.

python3 run_eval.py

Running process

Run the Claim Label Prediction Task for Tables

python3 run_claim_table.py

Run the Claim Label Prediction Task for Charts

python3 run_claim_img.py

Combination

python3 run_claim_combine.py

Evaluation

python3 run_eval.py

Citation

Please cite our paper as follows:

@article{Ho_Wu_Kumar_Boudin_Takasu_Aizawa_2026,
  title={Format Matters: The Robustness of Multimodal LLMs in Reviewing Evidence from Tables and Charts},
  volume={40},
  url={https://ojs.aaai.org/index.php/AAAI/article/view/40361},
  DOI={10.1609/aaai.v40i37.40361},
  number={37}, journal={Proceedings of the AAAI Conference on Artificial Intelligence},
  author={Ho, Xanh and Wu, Yun-Ang and Kumar, Sunisth and Boudin, Florian and Takasu, Atsuhiro and Aizawa, Akiko},
  year={2026},
  month={Mar.},
  pages={31014-31022}
}

The structure of the code in this repository is based on: https://github.com/Alab-NII/SciTabAlign

About

The Robustness of Multimodal LLMs in Reviewing Evidence from Tables and Charts

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages