Metraipolis › archive › dc_ecb679ef7f99

STRUCTURALCOST: A controlled reading time dataset for modeling human sentence processing difficulty — arXiv:2610.08208

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.08208
License (as archived): CC0-1.0
Archived: 2026-10-07T11:21:35.339Z
SHA-256 of the archived text: 69921aa152b7045890631108ebec6e9fcbb527a8c640e712fd041c8778b1c1b6
Stable URL of this page: https://metraipolis.com/documento/dc_ecb679ef7f99

How to cite

STRUCTURALCOST: A controlled reading time dataset for modeling human sentence processing difficulty — arXiv:2610.08208 — arXiv (en), https://arxiv.org/abs/2610.08208 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ecb679ef7f99 (Metraipolis archive dc_ecb679ef7f99, sha256 69921aa152b7045890631108ebec6e9fcbb527a8c640e712fd041c8778b1c1b6)

BibTeX

@misc{dcecb679ef7f99,
  title = {STRUCTURALCOST: A controlled reading time dataset for modeling human sentence processing difficulty — arXiv:2610.08208},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08208},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ecb679ef7f99; sha256 69921aa152b7045890631108ebec6e9fcbb527a8c640e712fd041c8778b1c1b6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08208. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce STRUCTURALCOST, a self-paced reading dataset of 475 participants and 40,800 observations isolating the processing cost of long-distance subject-verb dependency resolution. We replicate a low-powered psycholinguistic finding at NLP scale, namely that human reading times at the main verb increase with dependency length, driven by syntactic embedding beyond linear distance. Different language models -- spanning n-gram models, SSMs, and transformers -- partially mirror this graded difficulty profile, yet underestimate the integration cost humans incur, with a gap that persists across architectures and model sizes. This suggests these models capture the predictive component of human processing but not the full integration cost that working memory imposes. STRUCTURALCOST provides data needed to drive progress toward evaluating the cognitive plausibility of language models.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.08208 — 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 2026-10-07T11:15:24.807Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).