Metraipolis › archive › dc_ce1194add4e8

Representing Visual Evidence for Item Difficulty Prediction: Visual Textualization and Image-Native Modeling — arXiv:2608.04554

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.04554
License (as archived): CC0-1.0
Archived: 2026-10-31T11:24:41.940Z
SHA-256 of the archived text: 94c2e371fa172358238e5430da5a872580e64a5518c3a1120c558c7fffbf68d4
Stable URL of this page: https://metraipolis.com/documento/dc_ce1194add4e8

How to cite

Representing Visual Evidence for Item Difficulty Prediction: Visual Textualization and Image-Native Modeling — arXiv:2608.04554 — arXiv (en), https://arxiv.org/abs/2608.04554 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce1194add4e8 (Metraipolis archive dc_ce1194add4e8, sha256 94c2e371fa172358238e5430da5a872580e64a5518c3a1120c558c7fffbf68d4)

BibTeX

@misc{dcce1194add4e8,
  title = {Representing Visual Evidence for Item Difficulty Prediction: Visual Textualization and Image-Native Modeling — arXiv:2608.04554},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04554},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce1194add4e8; sha256 94c2e371fa172358238e5430da5a872580e64a5518c3a1120c558c7fffbf68d4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04554. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Predicting item difficulty from content can provide an initial estimate for newly developed questions before sufficient student responses are available. Existing approaches typically represent the question stem and answer choices as text. When mathematics items contain visual components, a common pipeline first textualizes that evidence and then applies a text predictor. We ask: how should visual evidence be represented for item difficulty prediction? We compare question text alone, visual textualization, which expresses visual evidence in language, and image-native modeling, which retains the original image. Using Eedi items with difficulty calibrated from student responses, we train large language models (LLMs) and vision-language models (VLMs) directly for difficulty regression. Both visual interfaces achieve the lowest point estimates, although the leading systems cannot be reliably ordered. Open-VLM textualization yields lower RMSE point estimates for all evaluated LLMs, while broader adaptation does so for all image-native VLMs. Test-time interventions show dependence on the paired full-item image, but do not isolate the additional visual component. The two visual interfaces also make partially complementary item-level errors and differ substantially in computational workflow. Thus, textualization should not be treated as the only practical interface: image-native modeling is a competitive alternative whose effectiveness depends on how the VLM is adapted.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.04554 — 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 2026-10-31T11:13:23.175Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).