@article{lostinthepipelinehowwelldolargelanguagem,
  title = {Lost in the Pipeline: How Well Do Large Language Models Handle Data Preparation?},
  author = {Matteo Spreafico and Ludovica Tassini and Camilla Sancricca and Cinzia Cappiello},
  year = {2025},
  eprint = {2511.21708},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.21708},
}