Metraipolis › archive › dc_40480489c41f

A Polyphonic Conception of AI Understanding — arXiv:2609.36079

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36079
License (as archived)
CC0-1.0
Archived
2026-10-07T16:22:14.772Z
SHA-256 of the archived text
a6d63efc7f52990bd41bfb5bf91ff7d7d5e292faa4976e95d4b7a2b8e6c67b3f
Stable URL of this page
https://metraipolis.com/documento/dc_40480489c41f

How to cite

A Polyphonic Conception of AI Understanding — arXiv:2609.36079 — arXiv (en), https://arxiv.org/abs/2609.36079 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_40480489c41f (Metraipolis archive dc_40480489c41f, sha256 a6d63efc7f52990bd41bfb5bf91ff7d7d5e292faa4976e95d4b7a2b8e6c67b3f)
BibTeX
@misc{dc40480489c41f,
  title = {A Polyphonic Conception of AI Understanding — arXiv:2609.36079},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36079},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_40480489c41f; sha256 a6d63efc7f52990bd41bfb5bf91ff7d7d5e292faa4976e95d4b7a2b8e6c67b3f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36079. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

When a doctor, a judge, or an engineer must decide whether to trust an AI model's output, they cannot avoid asking what the model understands. Purely mathematical or statistical descriptions struggle to distinguish trustworthy from untrustworthy outputs without reintroducing the question of AI understanding in all but name. Yet the question is ill-framed as it stands, because the inherited concept operates within a monophonic paradigm: the idea that a cognitive system's understanding of something must be localised to a single mechanism underpinning all the capacities conferred by such understanding. Drawing on a wide range of mechanistic evidence, we show that LLMs are pervasively polyphonic: outputs emerge from coalitions of parallel mechanisms of uneven reliability, which variously complement, duplicate, or drown out one another, with several coalitions sufficing for a task without any one being indispensable. Polyphony not only complicates attributions of understanding, but renders monophonic inference patterns hazardous. In response, we develop a conception of understanding fit for polyphonic AI. It centres on sound circuitry that is reliably and correctly recruited and in control of outputs. Attributions of understanding thereby become tractable claims about internal organisation, and can do the work of guiding trust in AI.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.36079 — 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 2026-10-07T15:54:53.464Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).