b08e1b1d3e0b52c2f09e · A Large-Scale Study of Relevance Assessments with Large Language Models: An Initial Look

{
  "title_en": "A Large-Scale Study of Relevance Assessments with Large Language Models: An Initial Look",
  "designation": "",
  "series": "",
  "status": "",
  "date": "2025-07-18",
  "date_original": "July 18, 2025",
  "url": "https://www.nist.gov/publications/large-scale-study-relevance-assessments-large-language-models-initial-look",
  "source": "NIST Publications",
  "display_en": "",
  "authors_en": "Shivani Upadhyay, Ronak Pradeep, Nandan Thakur, Daniel Campos, Nick Craswell, Ian Soboroff , Hoa Dang , Jimmy Lin",
  "abstract_excerpt_en": "The application of large language models to provide relevance assessments presents exciting opportunities to advance IR, NLP, and beyond, but to date many unknowns remain. In this paper, we report on the results of a large-scale evaluation (the TREC 2024",
  "id": "b08e1b1d3e0b52c2f09e",
  "sources": [
    "NIST Publications"
  ],
  "source_records": [
    {
      "title_en": "A Large-Scale Study of Relevance Assessments with Large Language Models: An Initial Look",
      "designation": "",
      "series": "",
      "status": "",
      "date": "2025-07-18",
      "date_original": "July 18, 2025",
      "url": "https://www.nist.gov/publications/large-scale-study-relevance-assessments-large-language-models-initial-look",
      "source": "NIST Publications",
      "display_en": "",
      "authors_en": "Shivani Upadhyay, Ronak Pradeep, Nandan Thakur, Daniel Campos, Nick Craswell, Ian Soboroff , Hoa Dang , Jimmy Lin",
      "abstract_excerpt_en": "The application of large language models to provide relevance assessments presents exciting opportunities to advance IR, NLP, and beyond, but to date many unknowns remain. In this paper, we report on the results of a large-scale evaluation (the TREC 2024"
    }
  ],
  "translation_state": "none"
}