Metraipolis › archive › dc_ea8bf9c9bc17

Reader Proficiency Shapes Layer-wise Surprisal Profiles — arXiv:2609.37688

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.37688
License (as archived)
CC0-1.0
Archived
2026-10-07T16:57:06.484Z
SHA-256 of the archived text
315c685f71b28452279b22c42eb54c84b56f9fae5763a1c215cd75a81510c7ce
Stable URL of this page
https://metraipolis.com/documento/dc_ea8bf9c9bc17

How to cite

Reader Proficiency Shapes Layer-wise Surprisal Profiles — arXiv:2609.37688 — arXiv (en), https://arxiv.org/abs/2609.37688 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea8bf9c9bc17 (Metraipolis archive dc_ea8bf9c9bc17, sha256 315c685f71b28452279b22c42eb54c84b56f9fae5763a1c215cd75a81510c7ce)
BibTeX
@misc{dcea8bf9c9bc17,
  title = {Reader Proficiency Shapes Layer-wise Surprisal Profiles — arXiv:2609.37688},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37688},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea8bf9c9bc17; sha256 315c685f71b28452279b22c42eb54c84b56f9fae5763a1c215cd75a81510c7ce},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37688. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reading behaviour varies not only with linguistic input, but also with reader proficiency. In this study, we investigate whether the layer-wise relationship between surprisal from large language models (LLMs) and human gaze behaviour differs across readers with different levels of proficiency and across gaze measures. Using eye-tracking data from the MECO L2 corpus, we compare readers with high and low vocabulary proficiency on first-pass gaze duration (FPGD) and total gaze duration (TGD). We quantify the distribution of the predictive power of surprisal across model layers using Predictive Depth. Across 12 tested LLMs, we find that readers with lower vocabulary proficiency tend to show deeper Predictive Depth for FPGD, while this difference is smaller for TGD. Also, TGD itself shows deeper Predictive Depth than FPGD in both proficiency groups. These patterns suggest that where predictive power is concentrated across LLM layers may be related to the timing and breadth of the reading processes captured by different gaze measures, and that this relationship can vary with reader proficiency. Our leave-one-out analysis further shows that the advantage of informative internal layers extends to unseen texts, although the practical improvements in prediction are limited. Overall, our results show that layer-wise LLM surprisal provides a useful perspective on variation in reading behaviour across both reader groups and gaze measures.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.37688 — 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 2026-10-07T16:27:03.326Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).