@misc{dl3-a05-1,
  title = {An Explanation of In-context Learning as Implicit Bayesian Inference},
  author = {Sang Michael Xie and Aditi Raghunathan and Percy Liang and Tengyu Ma},
  year = {2021},
  url = {https://arxiv.org/abs/2111.02080},
  howpublished = {arXiv primary author manuscript},
  archivePrefix = {arXiv},
  eprint = {2111.02080},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}

@misc{dl3-a05-2,
  title = {What Can Transformers Learn In-Context? A Case Study of Simple Function Classes},
  author = {Shivam Garg and Dimitris Tsipras and Percy Liang and Gregory Valiant},
  year = {2022},
  url = {https://arxiv.org/abs/2208.01066},
  howpublished = {arXiv primary author manuscript},
  archivePrefix = {arXiv},
  eprint = {2208.01066},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}

@misc{dl3-a05-3,
  title = {What learning algorithm is in-context learning? Investigations with linear models},
  author = {Ekin Akyürek and Dale Schuurmans and Jacob Andreas and Tengyu Ma and Denny Zhou},
  year = {2022},
  url = {https://arxiv.org/abs/2211.15661},
  howpublished = {arXiv primary author manuscript},
  archivePrefix = {arXiv},
  eprint = {2211.15661},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}

@misc{dl3-a05-4,
  title = {Transformers learn in-context by gradient descent},
  author = {Johannes von Oswald and Eyvind Niklasson and Ettore Randazzo and João Sacramento and Alexander Mordvintsev and Andrey Zhmoginov and Max Vladymyrov},
  year = {2022},
  url = {https://arxiv.org/abs/2212.07677},
  howpublished = {arXiv primary author manuscript},
  archivePrefix = {arXiv},
  eprint = {2212.07677},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}

@misc{dl3-a05-5,
  title = {Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?},
  author = {Sewon Min and Xinxi Lyu and Ari Holtzman and Mikel Artetxe and Mike Lewis and Hannaneh Hajishirzi and Luke Zettlemoyer},
  year = {2022},
  url = {https://arxiv.org/abs/2202.12837},
  howpublished = {arXiv primary author manuscript},
  archivePrefix = {arXiv},
  eprint = {2202.12837},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}

@misc{dl3-a05-6,
  title = {In-context Learning and Induction Heads},
  author = {Catherine Olsson and Nelson Elhage and Neel Nanda and Nicholas Joseph and Nova DasSarma and Tom Henighan and Ben Mann and Amanda Askell and Yuntao Bai and Anna Chen and Tom Conerly and Dawn Drain and Deep Ganguli and Zac Hatfield-Dodds and Danny Hernandez and Scott Johnston and Andy Jones and Jackson Kernion and Liane Lovitt and Kamal Ndousse and Dario Amodei and Tom Brown and Jack Clark and Jared Kaplan and Sam McCandlish and Chris Olah},
  year = {2022},
  url = {https://arxiv.org/abs/2209.11895},
  howpublished = {arXiv primary author manuscript},
  archivePrefix = {arXiv},
  eprint = {2209.11895},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}