Metraipolis › archive › dc_fe4dc4255689

Against All Likelihood — arXiv:2611.09385

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.09385
License (as archived)
CC0-1.0
Archived
2026-11-09T22:34:05.103Z
SHA-256 of the archived text
d700a6e8f7fed9219b9b7199cc72cb570f007954dc24b0746c3d5b3da9f59d58
Stable URL of this page
https://metraipolis.com/documento/dc_fe4dc4255689

How to cite

Against All Likelihood — arXiv:2611.09385 — arXiv (en), https://arxiv.org/abs/2611.09385 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fe4dc4255689 (Metraipolis archive dc_fe4dc4255689, sha256 d700a6e8f7fed9219b9b7199cc72cb570f007954dc24b0746c3d5b3da9f59d58)
BibTeX
@misc{dcfe4dc4255689,
  title = {Against All Likelihood — arXiv:2611.09385},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09385},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fe4dc4255689; sha256 d700a6e8f7fed9219b9b7199cc72cb570f007954dc24b0746c3d5b3da9f59d58},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09385. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Maximum likelihood is the dominant training principle for large language models, yet likelihood is neither necessary nor sufficient for truth. Unlikely events happen every day, and frequently repeated statements can be false. Drawing on a philosophical tradition that ties objectivity to invariance rather than probability (from Nozick's account of objective facts and Wigner's principles of invariance to the structural realism of Poincaré and Cassirer), we argue that the truth of a statement should be judged not by its probability under a single distribution, but by its invariance across relevant transformations of the environment. We connect this view to machine learning literature on out-of-distribution generalization and invariant learning, sketch how invariance could be tested at inference time with language models, and discuss implications for continual learning.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.09385 — 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 2026-11-09T22:30:47.278Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).