@misc{dl3-a02-1,
  title = {RoFormer: Enhanced Transformer with Rotary Position Embedding},
  author = {Jianlin Su and Yu Lu and Shengfeng Pan and Ahmed Murtadha and Bo Wen and Yunfeng Liu},
  year = {2021},
  url = {https://arxiv.org/abs/2104.09864},
  howpublished = {arXiv primary author manuscript},
  archivePrefix = {arXiv},
  eprint = {2104.09864},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}

@misc{dl3-a02-2,
  title = {Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation},
  author = {Ofir Press and Noah A. Smith and Mike Lewis},
  year = {2021},
  url = {https://arxiv.org/abs/2108.12409},
  howpublished = {arXiv primary author manuscript},
  archivePrefix = {arXiv},
  eprint = {2108.12409},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}

@misc{dl3-a02-3,
  title = {Extending Context Window of Large Language Models via Positional Interpolation},
  author = {Shouyuan Chen and Sherman Wong and Liangjian Chen and Yuandong Tian},
  year = {2023},
  url = {https://arxiv.org/abs/2306.15595},
  howpublished = {arXiv primary author manuscript},
  archivePrefix = {arXiv},
  eprint = {2306.15595},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}

@misc{dl3-a02-4,
  title = {YaRN: Efficient Context Window Extension of Large Language Models},
  author = {Bowen Peng and Jeffrey Quesnelle and Honglu Fan and Enrico Shippole},
  year = {2023},
  url = {https://arxiv.org/abs/2309.00071},
  howpublished = {arXiv primary author manuscript},
  archivePrefix = {arXiv},
  eprint = {2309.00071},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}

@misc{dl3-a02-5,
  title = {Lost in the Middle: How Language Models Use Long Contexts},
  author = {Nelson F. Liu and Kevin Lin and John Hewitt and Ashwin Paranjape and Michele Bevilacqua and Fabio Petroni and Percy Liang},
  year = {2023},
  url = {https://arxiv.org/abs/2307.03172},
  howpublished = {arXiv primary author manuscript},
  archivePrefix = {arXiv},
  eprint = {2307.03172},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}

@misc{dl3-a02-6,
  title = {Exploring Length Generalization in Large Language Models},
  author = {Cem Anil and Yuhuai Wu and Anders Andreassen and Aitor Lewkowycz and Vedant Misra and Vinay Ramasesh and Ambrose Slone and Guy Gur-Ari and Ethan Dyer and Behnam Neyshabur},
  year = {2022},
  url = {https://arxiv.org/abs/2207.04901},
  howpublished = {arXiv primary author manuscript},
  archivePrefix = {arXiv},
  eprint = {2207.04901},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}