[
  {
    "id": "dl3-a02-1",
    "type": "article",
    "title": "RoFormer: Enhanced Transformer with Rotary Position Embedding",
    "author": [
      {
        "literal": "Jianlin Su"
      },
      {
        "literal": "Yu Lu"
      },
      {
        "literal": "Shengfeng Pan"
      },
      {
        "literal": "Ahmed Murtadha"
      },
      {
        "literal": "Bo Wen"
      },
      {
        "literal": "Yunfeng Liu"
      }
    ],
    "issued": {
      "date-parts": [
        [
          2021
        ]
      ]
    },
    "URL": "https://arxiv.org/abs/2104.09864",
    "container-title": "arXiv primary author manuscript",
    "note": "Original arXiv bibliographic record and abstract inspected on 2026-10-28; full proof and source experiments not independently audited.",
    "archive": "arXiv",
    "archive_location": "2104.09864"
  },
  {
    "id": "dl3-a02-2",
    "type": "article",
    "title": "Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation",
    "author": [
      {
        "literal": "Ofir Press"
      },
      {
        "literal": "Noah A. Smith"
      },
      {
        "literal": "Mike Lewis"
      }
    ],
    "issued": {
      "date-parts": [
        [
          2021
        ]
      ]
    },
    "URL": "https://arxiv.org/abs/2108.12409",
    "container-title": "arXiv primary author manuscript",
    "note": "Original arXiv bibliographic record and abstract inspected on 2026-10-28; full proof and source experiments not independently audited.",
    "archive": "arXiv",
    "archive_location": "2108.12409"
  },
  {
    "id": "dl3-a02-3",
    "type": "article",
    "title": "Extending Context Window of Large Language Models via Positional Interpolation",
    "author": [
      {
        "literal": "Shouyuan Chen"
      },
      {
        "literal": "Sherman Wong"
      },
      {
        "literal": "Liangjian Chen"
      },
      {
        "literal": "Yuandong Tian"
      }
    ],
    "issued": {
      "date-parts": [
        [
          2023
        ]
      ]
    },
    "URL": "https://arxiv.org/abs/2306.15595",
    "container-title": "arXiv primary author manuscript",
    "note": "Original arXiv bibliographic record and abstract inspected on 2026-10-28; full proof and source experiments not independently audited.",
    "archive": "arXiv",
    "archive_location": "2306.15595"
  },
  {
    "id": "dl3-a02-4",
    "type": "article",
    "title": "YaRN: Efficient Context Window Extension of Large Language Models",
    "author": [
      {
        "literal": "Bowen Peng"
      },
      {
        "literal": "Jeffrey Quesnelle"
      },
      {
        "literal": "Honglu Fan"
      },
      {
        "literal": "Enrico Shippole"
      }
    ],
    "issued": {
      "date-parts": [
        [
          2023
        ]
      ]
    },
    "URL": "https://arxiv.org/abs/2309.00071",
    "container-title": "arXiv primary author manuscript",
    "note": "Original arXiv bibliographic record and abstract inspected on 2026-10-28; full proof and source experiments not independently audited.",
    "archive": "arXiv",
    "archive_location": "2309.00071"
  },
  {
    "id": "dl3-a02-5",
    "type": "article",
    "title": "Lost in the Middle: How Language Models Use Long Contexts",
    "author": [
      {
        "literal": "Nelson F. Liu"
      },
      {
        "literal": "Kevin Lin"
      },
      {
        "literal": "John Hewitt"
      },
      {
        "literal": "Ashwin Paranjape"
      },
      {
        "literal": "Michele Bevilacqua"
      },
      {
        "literal": "Fabio Petroni"
      },
      {
        "literal": "Percy Liang"
      }
    ],
    "issued": {
      "date-parts": [
        [
          2023
        ]
      ]
    },
    "URL": "https://arxiv.org/abs/2307.03172",
    "container-title": "arXiv primary author manuscript",
    "note": "Original arXiv bibliographic record and abstract inspected on 2026-10-28; full proof and source experiments not independently audited.",
    "archive": "arXiv",
    "archive_location": "2307.03172"
  },
  {
    "id": "dl3-a02-6",
    "type": "article",
    "title": "Exploring Length Generalization in Large Language Models",
    "author": [
      {
        "literal": "Cem Anil"
      },
      {
        "literal": "Yuhuai Wu"
      },
      {
        "literal": "Anders Andreassen"
      },
      {
        "literal": "Aitor Lewkowycz"
      },
      {
        "literal": "Vedant Misra"
      },
      {
        "literal": "Vinay Ramasesh"
      },
      {
        "literal": "Ambrose Slone"
      },
      {
        "literal": "Guy Gur-Ari"
      },
      {
        "literal": "Ethan Dyer"
      },
      {
        "literal": "Behnam Neyshabur"
      }
    ],
    "issued": {
      "date-parts": [
        [
          2022
        ]
      ]
    },
    "URL": "https://arxiv.org/abs/2207.04901",
    "container-title": "arXiv primary author manuscript",
    "note": "Original arXiv bibliographic record and abstract inspected on 2026-10-28; full proof and source experiments not independently audited.",
    "archive": "arXiv",
    "archive_location": "2207.04901"
  }
]