Metraipolis › archive › dc_a896227f511e

Objects Without Morphisms: What LLMs for Mathematics Do Not Represent — arXiv:2610.03551

Source
arXiv
Original
https://arxiv.org/abs/2610.03551
License (as archived)
CC0-1.0
Archived
2026-10-05T23:10:23.641Z
SHA-256 of the archived text
0ed4c8da1377b7e28453597983bbd3afe76b8716f7fa7850001795e15aa6eb30
Stable URL of this page
https://metraipolis.com/documento/dc_a896227f511e

How to cite

Objects Without Morphisms: What LLMs for Mathematics Do Not Represent — arXiv:2610.03551 — arXiv, https://arxiv.org/abs/2610.03551 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a896227f511e (Metraipolis archive dc_a896227f511e, sha256 0ed4c8da1377b7e28453597983bbd3afe76b8716f7fa7850001795e15aa6eb30)
BibTeX
@misc{dca896227f511e,
  title = {Objects Without Morphisms: What LLMs for Mathematics Do Not Represent — arXiv:2610.03551},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03551},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a896227f511e; sha256 0ed4c8da1377b7e28453597983bbd3afe76b8716f7fa7850001795e15aa6eb30},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03551. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) have reached expert-level performance on competition mathematics largely through the volume of search placed around them: candidate solutions are sampled in quantity and retained only when an external criterion accepts them. Such a procedure improves the outcome that survives it while leaving untouched what the model represents. We examine that question where no external criterion exists: translating statements between the dialects of neighbouring subfields, where fidelity turns on the level of generality at which content is asserted. The source leaves that level implicit in its vocabulary, so a faithful translation must recover it from the relation between the theories. We introduce an instrument that codes truth, content and scope in separate blind queues, with a judge-free measure of whether a rewrite states the hypothesis implicit in its source, and establish its sensitivity with a planted-positive control. Across seven models from four families, translating towards the general framing widens the domain of quantification in 60.6% of rewrites and narrows it in none; translating towards the concrete framing narrows it in 28.3% and widens it in 0.3%. The hypothesis that would prevent it is stated in 21.6% of model rewrites and 4.2% of human statements. Capability does not govern the asymmetry: it appears in every model tested, and the most capable widens least. It replicates on the half of the benchmark held out by a pre-registered rule, and on statements written by mathematicians. Instructing a model to state every hypothesis it requires raises that rate but not its sensitivity to direction. We argue that these systems have acquired an object-level correspondence between subfield vocabularies without the constraint under which a translation between theories carries hypotheses to hypotheses.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.03551 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-05T23:01:38.707Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).