@article{towardstransparencyexploringllmtrainings,
  title = {Towards Transparency: Exploring LLM Trainings Datasets through Visual Topic Modeling and Semantic Frame},
  author = {Charles de Dampierre and Andrei Mogoutov and Nicolas Baumard},
  year = {2024},
  eprint = {2406.06574},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.06574v1},
}