@article{howtransformersutilizemultiheadattention,
  title = {How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression},
  author = {Xingwu Chen and Lei Zhao and Difan Zou},
  year = {2024},
  eprint = {2408.04532},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2408.04532v1},
}