M3UCD: A Multi-task Multimodal Metaphor Understanding Challenge Dataset for LLMs
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (41) · 35030-35040
DOI: 10.1609/aaai.v40i41.40808 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Tianlong Zheng und 7 weiteren Autor:innen.
Abstract (Originalsprache)
Understanding multimodal metaphors represents a crucial pathway for machines to comprehend human cognition. However, current research remains constrained by superficial dataset annotations, insufficient systematic evaluation of large language models, and fragmented task frameworks. To bridge these gaps, the paper proposes a systematic solution featuring: (I) We present the largest fine-grained Multi-task Multimodal Metaphor Understanding Challenge Dataset (M3UCD) built via multi-perspective collaborative annotation. It contains 15,345 samples, each annotated with 12 manual attribute labels. (II) Systematic benchmarking of LLMs' capacity boundaries in metaphor understanding. Evaluation results reveal the persistent challenges LLMs face in this domain while validating M3UCD's effectiveness and potential. (III) A concise and unified multi-task baseline framework was developed and demonstrated its effectiveness in enhancing the metaphor understanding capabilities of MLLMs.
Zitieren
APA
Zheng, T., Yang, Y., Dong, R., Ma, B., Wang, L., Zhou, X., Miao, S., & Osman, T. (2026). M3UCD: A Multi-task Multimodal Metaphor Understanding Challenge Dataset for LLMs. Proceedings of the AAAI Conference on Artificial Intelligence, 40(41), 35030-35040. https://doi.org/10.1609/aaai.v40i41.40808
Vancouver
Zheng T, Yang Y, Dong R, Ma B, Wang L, Zhou X, et al. M3UCD: A Multi-task Multimodal Metaphor Understanding Challenge Dataset for LLMs. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(41):35030-35040. doi:10.1609/aaai.v40i41.40808
BibTeX
@article{Zheng2026,
author = {Zheng, Tianlong and Yang, Yating and Dong, Rui and Ma, Bo and Wang, Lei and Zhou, Xi and Miao, Siru and Osman, Turghun},
title = {M3UCD: A Multi-task Multimodal Metaphor Understanding Challenge Dataset for LLMs},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {41},
pages = {35030--35040},
doi = {10.1609/aaai.v40i41.40808}
}
EUVIMED