Metraipolis › archive › dc_f5ff8cfe99d3
PRISM: A Category-Theoretic Framework for Measuring and Refining Multimodal Analogies — arXiv:2610.01383
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.01383
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:04:55.721Z
- SHA-256 of the archived text
aa3441a9e832612de63af0459384d67460a0cdffba73f05d3ab07d46f868cf85- Stable URL of this page
https://metraipolis.com/documento/dc_f5ff8cfe99d3
How to cite
PRISM: A Category-Theoretic Framework for Measuring and Refining Multimodal Analogies — arXiv:2610.01383 — arXiv (en), https://arxiv.org/abs/2610.01383 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f5ff8cfe99d3 (Metraipolis archive dc_f5ff8cfe99d3, sha256 aa3441a9e832612de63af0459384d67460a0cdffba73f05d3ab07d46f868cf85)
BibTeX
@misc{dcf5ff8cfe99d3,
title = {PRISM: A Category-Theoretic Framework for Measuring and Refining Multimodal Analogies — arXiv:2610.01383},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.01383},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f5ff8cfe99d3; sha256 aa3441a9e832612de63af0459384d67460a0cdffba73f05d3ab07d46f868cf85},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01383. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Analogical reasoning involves identifying and preserving relational structures across domains. However, existing approaches to AI-driven multimodal analogy generation lack an interpretable measure of whether this structure is understood and maintained in the generated output. We address this gap with Pullback Refinement via Interpretable Structural Mapping (PRISM), a modality-agnostic framework for measuring and improving relational alignment in multimodal analogies, evaluated on visual metaphor generation. PRISM represents analogies as explicit relational mappings grounded in category theory and uses VLMs to instantiate these structures across modalities. Its first component, the pullback score, quantifies relational alignment from the resulting graph representation. On the AnaloBench benchmark, selecting the correct analogy purely by pullback score achieves 82.5% accuracy, demonstrating that the score captures meaningful relational information. PRISM's second component is an iterative refinement loop that uses the pullback score as an in-context feedback signal to iteratively revise the generated image towards greater relational depth. VLM-as-a-judge and human evaluations show that PRISM consistently improves metaphor consistency and analogy appropriateness over zero- shot generation, with human participants preferring the refined output in 57.65% of pairwise comparisons. However, a qualitative analysis reveals that refinement can favour visually crowded compositions rather than genuinely deeper relational correspondences. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.01383 — 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 2026-10-06T10:21:27.945Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).