Can MLLMs Decode the Creative Leap? Introducing C4 for Cross-Concept Understanding
Can MLLMs Decode the Creative Leap? Introducing C4 for Cross-Concept Understanding
Title: Can MLLMs Decode the Creative Leap? Introducing C4 for Cross-Concept Understanding Authors: Ming Wang, Yuqing Zhang, Tingna Xie, Xiangju Li, Xiaocui Yang, Daling Wang, Shi Feng, Yifei Zhang
标题： 多模态大模型能解码创造性飞跃吗？引入用于跨概念理解的 C4 框架 作者： Ming Wang, Yuqing Zhang, Tingna Xie, Xiangju Li, Xiaocui Yang, Daling Wang, Shi Feng, Yifei Zhang
Abstract: 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.
摘要： 多模态大模型（MLLMs）的创造性能力在设计、传播、教育和人机协作中至关重要，但由于缺乏明确的目标和奖励信号，其评估难度远高于以准确性为导向的任务。跨概念理解是支撑接受性创造力的核心认知能力，它使感知者能够从非显而易见但具有意义的概念关系中恢复出预期的含义。
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.
我们将题目构建操作化为“跨概念编码”，将模型推理操作化为“跨概念解码”。我们引入了 C4，这是一个受认知启发的评估框架，用于评估基于成语的跨概念创造力。其编码组件通过手动标注并经第三方审核的跨概念网络，将目标槽位映射到具有图像感的替代概念（桥接路径），从而实现具有明确结构、以桥接数量和深度为难度指标以及具备精确答案的批量生成。
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.
利用该框架，我们实例化了 C4 评估集（C4-Eval），包含 184 个合成题目和 37 个从网络收集的人工创作的跨概念成语图。我们为收集到的图形手动构建并审核了跨概念关系、桥接路径和推理过程。每个 C4-Eval 题目在五种任务设置下进行实例化，共产生 884 个主要答案恢复案例。
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.
在评估的十个多模态大模型中，最强的闭源模型主要准确率分别达到 50.7% 和 48.0%，而开源模型的表现则显著较低。候选约束能大幅提高准确率，但桥接提示和解释请求仅能带来微小的提升。这些结果揭示了当前多模态大模型在通过跨概念关系解码创造性编码含义方面存在巨大差距。代码已包含在补充材料中。