@misc{oban2024what,
  title={What do MLLMs hear? Examining reasoning with text and sound components in Multimodal Large Language Models},
  author={Enis Berk Çoban and Michael I. Mandel and Johanna Devaney},
  year={2024},
  eprint={2406.04615},
  archivePrefix={arXiv},
  primaryClass={eess.AS},
  url={https://arxiv.org/abs/2406.04615}
}