Metraipolis › archive › dc_aaf5dcc433de
Can MLLMs Decode the Creative Leap? Introducing C4 for Cross-Concept Understanding — arXiv:2608.06501
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.06501
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:47:07.194Z
- SHA-256 of the archived text
bcbbf764af7d0b834ef0801c515b72f28bb6958a11ced7e78d6cd382c3e864eb- Stable URL of this page
https://metraipolis.com/documento/dc_aaf5dcc433de
How to cite
Can MLLMs Decode the Creative Leap? Introducing C4 for Cross-Concept Understanding — arXiv:2608.06501 — arXiv (en), https://arxiv.org/abs/2608.06501 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aaf5dcc433de (Metraipolis archive dc_aaf5dcc433de, sha256 bcbbf764af7d0b834ef0801c515b72f28bb6958a11ced7e78d6cd382c3e864eb)
BibTeX
@misc{dcaaf5dcc433de,
title = {Can MLLMs Decode the Creative Leap? Introducing C4 for Cross-Concept Understanding — arXiv:2608.06501},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.06501},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aaf5dcc433de; sha256 bcbbf764af7d0b834ef0801c515b72f28bb6958a11ced7e78d6cd382c3e864eb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06501. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Creative capabilities of MLLMs matter in design, communication, education, and human--AI collaboration, yet remain difficult to evaluate because explicit targets and reward signals are scarce compared with accuracy-oriented tasks. Cross-concept understanding is a core cognitive capacity underlying receptive creativity. It enables a perceiver to recover intended meaning from non-obvious but meaningful conceptual relations. We operationalize item construction as cross-concept encoding and model inference as cross-concept decoding. We introduce C4, a cognition-inspired evaluation framework for Chengyu (Chinese idiom)-based Cross-Concept Creativity. Its encoding component maps target slots to imageable substitute concepts along bridge paths in a manually annotated and third-party-reviewed cross-concept network, enabling batch generation with explicit structure, difficulty indexed by bridge count and depth, and exact answers. Using this framework, we instantiate the C4 Evaluation Set (C4-Eval), comprising 184 synthetic items and 37 human-created cross-concept chengyu figures collected from online sources. We manually construct and review cross-concept relations, bridge paths, and reasoning processes for the collected figures. Each C4-Eval item is instantiated in five task settings, yielding 884 primary answer-recovery cases. Across ten evaluated MLLMs, the strongest closed models reach 50.7% and 48.0% primary accuracy, while open-source models remain substantially lower. Candidate constraints improve accuracy sharply, but bridge hints and explanation requests provide only modest gains. These results expose a substantial gap in how current MLLMs decode creatively encoded meaning through cross-concept relations. The code is in the supplementary material. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-10 in cs.CL). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Multimedia (cs.MM). Pagina del lavoro: https://arxiv.org/abs/2608.06501 — 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 2026-10-19T09:46:37.256Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).