Metraipolis › archive › dc_df0a0796a146

Deeply Interleaved Text-Image Contexts for Multimodal LLMs Assessment — arXiv:2609.02573

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02573
License (as archived)
CC0-1.0
Archived
2026-10-17T05:50:10.344Z
SHA-256 of the archived text
215d3b38cecb623dcb9db8d22d3fbcf900ba7b0f9574f47440cbd38f3af3f965
Stable URL of this page
https://metraipolis.com/documento/dc_df0a0796a146

How to cite

Deeply Interleaved Text-Image Contexts for Multimodal LLMs Assessment — arXiv:2609.02573 — arXiv (en), https://arxiv.org/abs/2609.02573 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_df0a0796a146 (Metraipolis archive dc_df0a0796a146, sha256 215d3b38cecb623dcb9db8d22d3fbcf900ba7b0f9574f47440cbd38f3af3f965)
BibTeX
@misc{dcdf0a0796a146,
  title = {Deeply Interleaved Text-Image Contexts for Multimodal LLMs Assessment — arXiv:2609.02573},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02573},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_df0a0796a146; sha256 215d3b38cecb623dcb9db8d22d3fbcf900ba7b0f9574f47440cbd38f3af3f965},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02573. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Current evaluations and training of multimodal models predominantly focus on multi-image tasks, largely overlooking interleaved text-image scenarios. In such multi-image tasks, text typically serves merely as task instructions, lacking deep semantic interaction with the visual content. In contrast, realworld applications like text-image co-creation, character tracking, and spatial reconstruction require constant interaction between text and images. Consequently, models must possess a deep understanding of these interleaved contexts. To bridge this gap, we introduce a novel benchmark, TIC-Bench (deeply interleaved Text-Image Contexts), designed to evaluate the capability of models to integrate text-image clues and recover the ground truth facts within deeply interleaved contexts. This benchmark encompasses three core domains: Logical, Temporal, and Spatial Association, which are further categorized into eight specific types, comprising a total of 2,280 questions. We evaluated 10 state-of-the-art MLLMs and observed a substantial performance gap compared to human experts, together with persistent difficulties in integrating evidence distributed across interleaved visual and textual inputs. Ultimately, this benchmark provides a valuable analytical tool for assessing and advancing the ability of multimodal models to effectively integrate text and image information in deeply interleaved contexts. TIC-Bench is publicly available at this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.02573 — 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 2026-10-17T05:25:58.138Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).