{
  "abstract": "Objective: To synthesize agreement between generative large language models (LLMs) and human coders on psychological and clinical text across four tasks, and benchmark it against human–human agreement on identical texts.\n\nMethod: Preregistered on OSF (https://doi.org/10.17605/OSF.IO/Z63BS). Nine bibliographic sources were searched to October 21, 2026, plus citation searching. Eligible studies evaluated a generative LLM and human coders on identical text units using the same scheme. Correlated-and-hierarchical-effects models with cluster-robust variance estimation (CR2) pooled effect sizes.\n\nResults: Across 377 studies (416 reports), pooled chance-corrected agreement (kappa family) was 0.62 (95% CI [0.58, 0.65]; 107 studies, 595 estimates; 95% prediction interval [0.15, 1.00]). Agreement did not differ across tasks (codebook coding 0.63, assessment scoring 0.58, clinical rating 0.62, helper evaluation 0.59). Correlation/ICC pooled at 0.71 [0.66, 0.75] (95 studies). In 23 matched studies, LLMs agreed less with humans than humans with each other (&Delta;κ = −0.11 [−0.18, −0.03]); equivalence within ±0.10 could not be established for models from 2025 (&Delta;κ = −0.12, 90% CI [−0.19, −0.05]). Agreement did not improve with release date (+0.02/year, p = .282) or within-study model contrasts (−0.01 [−0.06, 0.03]); it tracked human reliability (slope = 0.63, p < .001) and was higher for manifest than latent constructs (+0.09, p = .028). Percentage agreement exceeded kappa by 0.24 in the same configurations. Certainty (GRADE) was low to very low.\n\nConclusions: Generative LLMs achieve moderate-to-substantial agreement but remain, on average, below human inter-rater reliability. Agreement did not change across model release dates. Validation studies must report chance-corrected metrics and human benchmarks on identical units.",
  "abstract_shown": true,
  "affiliations": [
    "Turan University"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Martin Rekhert",
      "orcid": "0009-0001-2402-2031"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0f47dxd87z8n8.bib",
  "cited_by": 0,
  "doi": "10.5281/zenodo.23613737",
  "fulltext_url": null,
  "id": "0f47dxd87z8n8",
  "issns": [],
  "landing_url": "https://zenodo.org/records/23613737",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [],
  "openalex": null,
  "pdf_url": "https://zenodo.org/api/records/23613737/files/Rekhert_2026_llm_coder_agreement_preprint.pdf/content",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-24",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0f47dxd87z8n8.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T12:21:26Z",
      "native_id": "23613737",
      "source": "zenodo",
      "url": "https://zenodo.org/records/23613737"
    }
  ],
  "subjects": [],
  "title": "Agreement between large language models and human coders on psychological and clinical text: a systematic review and multilevel meta-analysis",
  "title_text": "Agreement between large language models and human coders on psychological and clinical text: a systematic review and multilevel meta-analysis",
  "type": "preprint",
  "updated_at": "2026-11-07T12:21:26Z",
  "url": "https://research.draconitic.com/paper/0f47dxd87z8n8",
  "venue": "Zenodo",
  "versions": []
}