Metraipolis › archive › dc_1365e30ff417

Illusory Pattern Perception Drives Spurious Inference in Large Language Models — arXiv:2610.07791

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.07791
License (as archived)
CC0-1.0
Archived
2026-10-07T11:19:08.890Z
SHA-256 of the archived text
f6d53980e2ab979c8087574f264c4402b36c626a877130861256ea0ec31b7d20
Stable URL of this page
https://metraipolis.com/documento/dc_1365e30ff417

How to cite

Illusory Pattern Perception Drives Spurious Inference in Large Language Models — arXiv:2610.07791 — arXiv (en), https://arxiv.org/abs/2610.07791 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1365e30ff417 (Metraipolis archive dc_1365e30ff417, sha256 f6d53980e2ab979c8087574f264c4402b36c626a877130861256ea0ec31b7d20)
BibTeX
@misc{dc1365e30ff417,
  title = {Illusory Pattern Perception Drives Spurious Inference in Large Language Models — arXiv:2610.07791},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07791},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1365e30ff417; sha256 f6d53980e2ab979c8087574f264c4402b36c626a877130861256ea0ec31b7d20},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07791. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Illusory pattern perception is a well-documented human cognitive tendency to infer meaningful relationships in data that is actually random. Such a tendency, often described as "connecting the dots" where none exist, can result in systematic reasoning errors. This paper investigates whether Large Language Models (LLMs) exhibit such perceptual tendencies, which can lead to systematic errors in downstream applications. To our knowledge, this work presents the first systematic study of illusory pattern perception in LLMs, adapting classic psychological paradigms to three tasks with direct empirical comparison to human behaviors. We find that LLMs frequently exhibit stronger illusory pattern perception than humans. In particular, models tend to over-associate frequent positive attributes with majority groups or large organizations, and show increased tendencies to construct causal narratives from ambiguous events. To uncover the mechanism behind these behaviors, we develop a feature interpretability framework based on Sparse Autoencoders (SAEs) to analyze internal representations. Our results reveal that holistic frequency perception and analytic cognitive orientation are linked to the emergence of illusory perceptions. These findings highlight a previously underexplored cognitive-like illusion that may affect the reliability of LLM reasoning. Code available at this https URL .

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/2610.07791 — 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 2026-10-07T11:15:24.556Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).