{
  "abstract": "The introduction of generative large language models (LLMs) has led to the exploration of their use in evidence synthesis tasks, such as literature searches, 1 screening,2 3 risk of bias assessment,4 5 data extraction,6–9 statistical analysis8 and writing plain language summaries.10 Of these tasks, data extraction (ie, transferring data from reports of primary studies into standardised tables) is a crucial, yet time-consuming11 and error-prone12 step in the evidence synthesis process.",
  "authors": [
    {
      "affiliations": [
        "RTI International, Research Triangle Park, North Carolina, USA",
        "Department for Evidence-based Medicine and Evaluation, University for Continuing Education Krems, Krems, Austria"
      ],
      "name": "Gerald Gartlehner"
    },
    {
      "affiliations": [
        "RTI International, Research Triangle Park, North Carolina, USA"
      ],
      "name": "Leila Kahwati"
    },
    {
      "affiliations": [
        "Department for Evidence-based Medicine and Evaluation, University for Continuing Education Krems, Krems, Austria"
      ],
      "name": "Barbara Nussbaumer-Streit"
    },
    {
      "affiliations": [
        "RTI International, Research Triangle Park, North Carolina, USA"
      ],
      "name": "Karen Crotty"
    },
    {
      "affiliations": [
        "RTI International, Research Triangle Park, North Carolina, USA"
      ],
      "name": "Rainer Hilscher"
    },
    {
      "affiliations": [
        "RTI International, Research Triangle Park, North Carolina, USA"
      ],
      "name": "Shannon Kugley"
    },
    {
      "affiliations": [
        "RTI International, Research Triangle Park, North Carolina, USA"
      ],
      "name": "Meera Viswanathan"
    },
    {
      "affiliations": [
        "RTI International, Research Triangle Park, North Carolina, USA"
      ],
      "name": "Ian Thomas"
    },
    {
      "affiliations": [
        "RTI International, Research Triangle Park, North Carolina, USA"
      ],
      "name": "Amanda Konet"
    },
    {
      "affiliations": [
        "RTI International, Research Triangle Park, North Carolina, USA"
      ],
      "name": "Graham Booth"
    },
    {
      "affiliations": [
        "RTI International, Research Triangle Park, North Carolina, USA"
      ],
      "name": "Robert Chew"
    }
  ],
  "title": "From promise to practice: challenges and pitfalls in the evaluation of large language models for data extraction in evidence synthesis",
  "uid": "4e5c969a-7b7d-547a-89d3-cd3075e31e9e"
}