{
  "abstract": "Models (VLMs) combined using a Bayesian statistical framework can classify galaxy merger morphologies with accuracy comparable to trained human experts. We deploy 15 VLM classifier configurations, spanning four model architectures (Gemma-4 E2B, Gemma-4 E4B, Qwen2.5-VL, and Qwen3-VL) tested with up to four prompt engineering strategies each. We evaluate their performance against a truth-known sample of 41 VELA+SUNRISE mock galaxy images from Lambrides et al. (2021a). As a proof-of-concept, all validation is performed on these mock images; application to real observational samples will require additional calibration and observational validation. The VLM ensemble achieves 83.3% accuracy on confident classifications (merger probability pM >= 0.8 or pM <= 0.2) and 58.3% completeness, with 5 misclassified galaxies, compared to 85% for both human accuracy and completeness. The ensemble recovers the population merger fraction to within 0.66 sigma of the truth (fM = 0.52 +/- 0.09 vs. true value of 0.585). Bayesian weighting improves overall accuracy by 17.1 percentage points over simple majority voting, with sensitivity improving by 29.2 percentage points. The ensemble produces 5 misclassifications (2 false positives, 3 false negatives), comparable to the 6 misclassifications (5 false positives, 1 false negative) reported for human classifiers by L21. The error-profile differences are not statistically significant for this sample. VLMs also produce more moderate per-galaxy merger probability distributions (27% uncertain) than the more polarized human distributions (15% uncertain), though this difference is also consistent with statistical fluctuation. These results establish VLMs as scalable, reproducible alternatives to human classifiers within a Bayesian probabilistic merger-fraction framework, for large-survey applications.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2606.00415",
  "author_total": 4,
  "authors": [
    {
      "name": "Marco Chiaberge"
    },
    {
      "name": "Elias Stengel-Eskin"
    },
    {
      "name": "Massimo Stiavelli"
    },
    {
      "name": "Colin Norman"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5mh8ntc0ce466.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2606.00415",
  "fulltext_url": null,
  "id": "5mh8ntc0ce466",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2606.00415",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "astro-ph.GA"
    ],
    [
      "arxiv",
      "astro-ph.IM"
    ],
    [
      "openalex",
      "3103|Galaxies: Formation, Evolution, Phenomena"
    ]
  ],
  "openalex": "W7163136366",
  "pdf_url": "https://arxiv.org/pdf/2606.00415",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-24",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/5mh8ntc0ce466.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:52Z",
      "native_id": "2606.00415",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2606.00415"
    }
  ],
  "subjects": [
    {
      "field": "astronomy",
      "origin": "arxiv:astro-ph.GA",
      "subfield": "galaxies"
    },
    {
      "field": "astronomy",
      "origin": "arxiv:astro-ph.IM",
      "subfield": "instrumentation-methods"
    }
  ],
  "title": "Vision-Language Model Ensembles Achieve Human-Expert Accuracy for Galaxy Merger Classification",
  "title_text": "Vision-Language Model Ensembles Achieve Human-Expert Accuracy for Galaxy Merger Classification",
  "type": "preprint",
  "updated_at": "2026-11-06T18:21:30Z",
  "url": "https://research.draconitic.com/paper/5mh8ntc0ce466",
  "venue": "arXiv",
  "versions": []
}