{
  "abstract": "Large language models (LLMs) are increasingly proposed as priors for cold-starting Bayesian optimization (BO) of chemical reactions, yet their benefit–risk profile in multi-objective reaction optimization remains poorly characterized. We present a systematic benchmark asking when LLM knowledge helps, is neutral, or hurts multi-objective BO (MOBO). Across seven public reaction benchmarks (6,384 candidate experiments), we compare nine strategies—including LLM-initialized BO, an LLM-only initializer, and established baselines (TSEMO, EDBO+-style scalarization, LLAMBO)—with 20 seeds per configuration (1,120 main-grid plus 360 ablation campaigns), scored by hypervolume completion and its sampling-efficiency integral (AUC), with paired Wilcoxon tests and two-family Benjamini–Hochberg correction against a random-init BO control. Three regimes emerge. On Suzuki–Miyaura, LLM initialization significantly improves sampling efficiency (ΔAUC +2.0 points, q = 0.026; alternative backbone +2.7 points, q = 1.4 × 10⁻⁴). On Buchwald–Hartwig, LLM priors are statistically indistinguishable from random. On a process-development coupling, LLM initialization significantly harms efficiency (ΔAUC −11.1 points, q = 0.0016) despite a 0% out-of-pool rate, whereas the Suzuki benefit coexists with a 45% out-of-pool rate—the prior’s direction, not its syntactic validity, controls the outcome. Diversity-based initialization (farthest point sampling) matches or exceeds LLM initialization wherever LLMs help, and no LLM-derived benefit exceeds what the knowledge-free diversity control already provides. A five-category diagnostic protocol intercepts 100% out-of-pool suggestions on the flow cases at zero experimental cost. LLM priors are not yet a reliable default for multi-objective reaction optimization; we provide a cost-free pre-campaign screening heuristic for deciding when to trust them.",
  "abstract_shown": true,
  "affiliations": [
    "Independent Researcher"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Fan Zhang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/68w7ksa5vmd75.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15009537/v1",
  "fulltext_url": null,
  "id": "68w7ksa5vmd75",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009537/v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1703|Advanced Multi-Objective Optimization Algorithms"
    ]
  ],
  "openalex": "W7214664710",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009537/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-28",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/68w7ksa5vmd75.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:21Z",
      "native_id": "10.26434/chemrxiv.15009537",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009537/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "source:chemrxiv",
      "subfield": "general"
    }
  ],
  "title": "Auditing LLM Chemical Priors for Multi-Objective Bayesian Optimization of Chemical Reactions: A Validity, Alignment, and Diversity Benchmark",
  "title_text": "Auditing LLM Chemical Priors for Multi-Objective Bayesian Optimization of Chemical Reactions: A Validity, Alignment, and Diversity Benchmark",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:21Z",
  "url": "https://research.draconitic.com/paper/68w7ksa5vmd75",
  "venue": "ChemRxiv",
  "versions": []
}