Metraipolis › archive › dc_da4807f529a2

A Formal Limitation on Learning Human Language From Textual Corpora — arXiv:2608.28560

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28560
License (as archived)
CC0-1.0
Archived
2026-10-17T10:56:40.575Z
SHA-256 of the archived text
50ea883d9d862fd69ea2c305c2e0e7656b3aaad97df5ec6a51957c70f2ca4a41
Stable URL of this page
https://metraipolis.com/documento/dc_da4807f529a2

How to cite

A Formal Limitation on Learning Human Language From Textual Corpora — arXiv:2608.28560 — arXiv (en), https://arxiv.org/abs/2608.28560 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da4807f529a2 (Metraipolis archive dc_da4807f529a2, sha256 50ea883d9d862fd69ea2c305c2e0e7656b3aaad97df5ec6a51957c70f2ca4a41)
BibTeX
@misc{dcda4807f529a2,
  title = {A Formal Limitation on Learning Human Language From Textual Corpora — arXiv:2608.28560},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28560},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da4807f529a2; sha256 50ea883d9d862fd69ea2c305c2e0e7656b3aaad97df5ec6a51957c70f2ca4a41},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28560. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Can a listener recover what a speaker means from the form of an utterance alone? We answer this question information-theoretically, and for a listener given by any featurizer of text, including the hidden states of contemporary large language models. Modeling language use as a joint distribution over meanings, contexts, and utterances, we derive upper bounds on the probability that a decoder recovers a speaker's intended meaning from a representation of the utterance. The bounds are governed by the uncertainty that form leaves about meaning, which splits into an irreducible part and a part that only (extralinguistic) context, but never the utterance alone, can resolve. Because these quantities are intrinsic to language, no representation, however much text or supervision produced it, can surpass them. The bounds apply, moreover, to meaning spaces that are discrete or continuous. We provide empirical evidence in support of the theory through experiments on artificial languages, Mandarin zero-pronoun resolution, and color reference.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.28560 — 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 2026-10-17T10:47:33.150Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).