{
  "abstract": "Large language models can interpret natural lan- guage, yet robust decisions remain challenging. Jev-like models expose structured choices, but these interfaces do not directly provide numeri- cal values at a requested precision. We propose NUMERICJEV, a training-free numerical decod- ing algorithm that enables numerical output from any LLM with a Jev-like structured-choice in- terface. Surprisingly, on our arithmetic bench- mark, it outperforms direct selection from a can- didate list containing the correct answer by 2.93 percentage points (Figure 1). Our motivation comes from the observation that numerical range selection is itself a decision problem that Jev- like LLMs can address. NUMERICJEV recur- sively refines a range through a multiway deci- sion tree while retaining the original question in context, without parameter updates or hidden- state access. On a 100-value grid, a ten-way tree requires only two decision rounds. Range- normalized MAE is 1.84% versus 5.18% for di- rect choice. A separate three-date historical- index study yields 4.58% mean relative recall er- ror and 0% readout error when the value is sup- plied. Code is available at https://github. com/Bring-AI/jev-numeric.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.28587",
  "author_total": 3,
  "authors": [
    {
      "name": "Weiwei Ye"
    },
    {
      "name": "Hangchen Liu"
    },
    {
      "name": "Renhe Jiang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/exdhvvkwwaxmq.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.28587",
  "fulltext_url": null,
  "id": "exdhvvkwwaxmq",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.28587",
  "language": null,
  "licence": "CC-BY-NC-SA-4.0",
  "licence_label": "CC BY-NC-SA 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Topic Modeling"
    ]
  ],
  "openalex": "W7214352357",
  "pdf_url": "https://arxiv.org/pdf/2609.28587",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-23",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/exdhvvkwwaxmq.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:21Z",
      "native_id": "2609.28587",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.28587"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "NumericJev: Jev-like LLM Numerical Decoding with Multiway Decision Trees",
  "title_text": "NumericJev: Jev-like LLM Numerical Decoding with Multiway Decision Trees",
  "type": "preprint",
  "updated_at": "2026-10-30T12:24:21Z",
  "url": "https://research.draconitic.com/paper/exdhvvkwwaxmq",
  "venue": "arXiv",
  "versions": []
}