{
  "abstract": "Astronomical observations include images, spectra, and light curves, while the scientific literature describes these objects in natural language. We present AstroBridge, a framework that connects these observations to an LLM through a literature-assisted caption generation pipeline. We used catalog metadata to match observations with scientific texts that describe the same objects. A vision-language model generates descriptive captions from representations of observations, matched passages, and available metadata, creating observation-caption pairs without manual captioning. We train AstroBridge to predict captions directly from raw observations. Modality-specific frozen encoders extract representations that a shared, trainable fusion network aligns with the embedding space of an LLM. In caption-based evaluation of spectra, AstroBridge achieves 91.5% accuracy in distinguishing quasars from galaxies, compared to 69.0% from the base model prior to fine-tuning. Limitations remain in galaxy morphology, classification of minority supernova classes, and the factual quality of generated captions. We believe that AstroBridge's framework is a step towards the goal of aligning the totality of astronomy's diverse, exotic data through the lingua franca of text.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.36375",
  "author_total": 14,
  "authors": [
    {
      "name": "Ibrahim Habib"
    },
    {
      "name": "Kevin Li"
    },
    {
      "name": "Trung Nguyen"
    },
    {
      "name": "Gabriel A. Patron"
    },
    {
      "name": "Gaurav Sekar"
    },
    {
      "name": "Nolan Koblischke"
    },
    {
      "name": "Matthieu Le Lain"
    },
    {
      "name": "Shashwat Sourav"
    },
    {
      "name": "Aman Kumar"
    },
    {
      "name": "Kartheik G. Iyer"
    },
    {
      "name": "Joshua S. Speagle"
    },
    {
      "name": "Itai Sfaradi"
    },
    {
      "name": "Michael J. Smith"
    },
    {
      "name": "Ioana Ciucă"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9ncawate5yd0e.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.36375",
  "fulltext_url": null,
  "id": "9ncawate5yd0e",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.36375",
  "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.IM"
    ],
    [
      "openalex",
      "1707|Multimodal Machine Learning Applications"
    ]
  ],
  "openalex": "W7224078018",
  "pdf_url": "https://arxiv.org/pdf/2610.36375",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-26",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/9ncawate5yd0e.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:35:50Z",
      "native_id": "2610.36375",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.36375"
    }
  ],
  "subjects": [
    {
      "field": "astronomy",
      "origin": "arxiv:astro-ph.IM",
      "subfield": "instrumentation-methods"
    }
  ],
  "title": "The Great Chat in the Sky: Aligning Exotic Astronomical Data to Language with AstroBridge",
  "title_text": "The Great Chat in the Sky: Aligning Exotic Astronomical Data to Language with AstroBridge",
  "type": "preprint",
  "updated_at": "2026-10-30T12:35:50Z",
  "url": "https://research.draconitic.com/paper/9ncawate5yd0e",
  "venue": "arXiv",
  "versions": []
}