Hugging Face Daily Papers · · 4 min read

Can MLLMs Decode the Creative Leap? Introducing C4 for Cross-Concept Understanding

Mirrored from Hugging Face Daily Papers for archival readability. Support the source by reading on the original site.

Inspired by cognitive science, we used Chinese idioms (or Chengyu) as a vehicle to design a cross-concept comprehension task as an anchor for assessing the creative ability of MLLMs, and we created a leaderboard.</p>\n","updatedAt":"2026-08-10T05:01:37.756Z","author":{"_id":"644378a96cea0db46dc96b39","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/644378a96cea0db46dc96b39/wjGNaXjfhSdWr8kM6Amai.jpeg","fullname":"Ming Wang","name":"sci-m-wang","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":4,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9539205431938171},"editors":["sci-m-wang"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/644378a96cea0db46dc96b39/wjGNaXjfhSdWr8kM6Amai.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.06501","authors":[{"_id":"6a7958fa8e9301703eaa5f71","user":{"_id":"644378a96cea0db46dc96b39","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/644378a96cea0db46dc96b39/wjGNaXjfhSdWr8kM6Amai.jpeg","isPro":false,"fullname":"Ming Wang","user":"sci-m-wang","type":"user","name":"sci-m-wang"},"name":"Ming Wang","status":"claimed_verified","statusLastChangedAt":"2026-08-10T08:45:04.388Z","hidden":false},{"_id":"6a7958fa8e9301703eaa5f72","name":"Yuqing Zhang","hidden":false},{"_id":"6a7958fa8e9301703eaa5f73","name":"Tingna Xie","hidden":false},{"_id":"6a7958fa8e9301703eaa5f74","name":"Xiangju Li","hidden":false},{"_id":"6a7958fa8e9301703eaa5f75","name":"Xiaocui Yang","hidden":false},{"_id":"6a7958fa8e9301703eaa5f76","name":"Daling Wang","hidden":false},{"_id":"6a7958fa8e9301703eaa5f77","name":"Shi Feng","hidden":false},{"_id":"6a7958fa8e9301703eaa5f78","name":"Yifei Zhang","hidden":false}],"publishedAt":"2026-08-06T00:00:00.000Z","submittedOnDailyAt":"2026-08-10T00:00:00.000Z","title":"Can MLLMs Decode the Creative Leap? Introducing C4 for Cross-Concept Understanding","submittedOnDailyBy":{"_id":"644378a96cea0db46dc96b39","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/644378a96cea0db46dc96b39/wjGNaXjfhSdWr8kM6Amai.jpeg","isPro":false,"fullname":"Ming Wang","user":"sci-m-wang","type":"user","name":"sci-m-wang"},"summary":"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.","upvotes":1,"discussionId":"6a7958fb8e9301703eaa5f79","organization":{"_id":"6a70927c8bfd8c53670018c1","name":"kinamind","fullname":"KinaMind","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/644378a96cea0db46dc96b39/waICbkYoR7UV7uT0q8SDK.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"644378a96cea0db46dc96b39","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/644378a96cea0db46dc96b39/wjGNaXjfhSdWr8kM6Amai.jpeg","isPro":false,"fullname":"Ming Wang","user":"sci-m-wang","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"6a70927c8bfd8c53670018c1","name":"kinamind","fullname":"KinaMind","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/644378a96cea0db46dc96b39/waICbkYoR7UV7uT0q8SDK.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.06501.md","query":{}}">
Papers
arxiv:2608.06501

Can MLLMs Decode the Creative Leap? Introducing C4 for Cross-Concept Understanding

Published on Aug 6
· Submitted by
Ming Wang
on Aug 10
Authors:

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. 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.

Community

Paper author Paper submitter about 6 hours ago

Inspired by cognitive science, we used Chinese idioms (or Chengyu) as a vehicle to design a cross-concept comprehension task as an anchor for assessing the creative ability of MLLMs, and we created a leaderboard.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images

· Sign up or log in to comment

Get this paper in your agent:

hf papers read 2608.06501
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper

No model linking this paper

Cite arxiv.org/abs/2608.06501 in a model README.md to link it from this page.

Datasets citing this paper

Spaces citing this paper

No Space linking this paper

Cite arxiv.org/abs/2608.06501 in a Space README.md to link it from this page.

Collections including this paper

No Collection including this paper

Add this paper to a collection to link it from this page.

Discussion (0)

Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.

Sign in →

No comments yet. Sign in and be the first to say something.

More from Hugging Face Daily Papers