arXiv cs.CL· Hong Jiang, Junnan Zhu, Jingwang Huang, Xiao Sun, Yuming Yang, Jiang Zhong, Ruirui Chen, Jingman Shi, Hao Wu, Nayu Liu, Xinyi Jiang, Kaiwen Wei·· 2 天前AI 评分21
M³R-Bench：面向证据溯源的多模态隐喻理解统一基准
M$^3$R-Bench: A Unified Benchmark for Evidence-Grounded Multimodal Metaphor Understanding
AI 导读
研究者推出 M³R-Bench，一个包含 1,000 个人工标注图文实例的基准，联合标注隐喻发生、Target-Source 映射与情感，并提供分阶段解释。
正文 · 原文
Authors:Hong Jiang, Junnan Zhu, Jingwang Huang, Xiao Sun, Yuming Yang, Jiang Zhong, Ruirui Chen, Jingman Shi, Hao Wu, Nayu Liu, Xinyi Jiang, Kaiwen Wei
Abstract:Multimodal metaphor understanding requires identifying cross-domain Target-Source mappings and inferring sentiment from visual and textual evidence. However, existing benchmarks largely evaluate these subtasks separately and lack evidence-grounded explanations, limiting their ability to assess coherent cross-modal reasoning. To enable unified and evidence-grounded evaluation, we introduce M$^3$R-Bench, a benchmark of 1,000 human-annotated image-text instances with joint labels for metaphor occurrence, Target-Source mapping, and sentiment, alongside stage-wise explanations for evidence identification, mapping establishment, and sentiment inference. Evaluations reveal that existing models frequently rely on textual shortcuts and produce Target-Source mappings inconsistent with visual evidence. To address this evidence-mapping mismatch, we propose M$^3$R-Reasoner, which combines curriculum-based reasoning supervision with task-aware reinforcement learning. Built on an 8B-parameter backbone, M$^3$R-Reasoner achieves 37.90% Joint Label Accuracy (JLA) metric, outperforming the strongest proprietary baseline by 19.50 percentage points. It further surpasses GPT-5.5 in image-text evidence and sentiment justification scores by 28.45 and 28.11 points, respectively. The dataset and code are available at this https URL.
| Comments: | 21 pages, 15 figures and 11 tables (including appendices). Hong Jiang, Junnan Zhu, and Jingwang Huang contributed equally. Jiang Zhong and Kaiwen Wei are corresponding authors. Code and data are available at this https URL |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2608.05817 [cs.CL] |
| (or arXiv:2608.05817v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2608.05817 arXiv-issued DOI via DataCite |
Submission history
From: Hong Jiang [view email]
[v1]
Thu, 6 Aug 2026 09:48:36 UTC (1,893 KB)
[v2]
Thu, 15 Oct 2026 07:46:25 UTC (1,024 KB)
来源：arXiv cs.CL · arxiv.org