ATProto Browser

{
  "text": "This #EMNLP2024 best paper aclanthology.org/2024.emnlp-m... had large gains over their (somewhat weak) baseline in trying to determine if a given document was in a LLMs pre-training data. Progress in an important problem.",
  "$type": "app.bsky.feed.post",
  "embed": {
    "$type": "app.bsky.embed.external",
    "external": {
      "uri": "https://aclanthology.org/2024.emnlp-main.300/",
      "thumb": {
        "$type": "blob",
        "ref": {
          "$link": "bafkreiglhrmfik7r4xsao63ysyvbt3wwmukrkfgzftxbmenmboae65vl7m"
        },
        "mimeType": "image/jpeg",
        "size": 473200
      },
      "title": "Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method",
      "description": "Weichao Zhang, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Yixing Fan, Xueqi Cheng. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024."
    }
  },
  "langs": [
    "en"
  ],
  "facets": [
    {
      "index": {
        "byteEnd": 15,
        "byteStart": 5
      },
      "features": [
        {
          "tag": "EMNLP2024",
          "$type": "app.bsky.richtext.facet#tag"
        }
      ]
    },
    {
      "index": {
        "byteEnd": 59,
        "byteStart": 27
      },
      "features": [
        {
          "uri": "https://aclanthology.org/2024.emnlp-main.300/",
          "$type": "app.bsky.richtext.facet#link"
        }
      ]
    }
  ],
  "createdAt": "2024-12-20T19:24:08.880Z"
}