M cubed R-Bench: A Unified Benchmark for Evidence-Grounded Multimodal Metaphor Understanding

arXiv:2608.05817 · cs.CL · Submitted 2026-08-06 · Read on arXiv

cs.CL

Submitted: 2026-08-06

Updated: 2026-10-15

Comments: 6 figures and 5 tables. Hong Jiang, Junnan Zhu, and Jingwang Huang contributed equally. Jiang Zhong and Kaiwen Wei are corresponding authors. Code and data are available at https://github.com/hongshi4/M3R-Bench

Code: https://github.com/hongshi4/M3R-Bench

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 27× in this paper · explained in 2 episodes
• MLLMs — 20× in this paper · explained in 2 episodes
• Visual Evidence — 15× in this paper
• Reinforcement Learning — 12× in this paper · explained in 4 episodes
• Grounding — 10× in this paper · explained in 3 episodes
• Accuracy — 6× in this paper · explained in 1 episode
• Sentiment Justification — 6× in this paper
• Metaphor Detection — 5× in this paper
• Core — 4× in this paper · explained in 2 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• GRPO — 4× in this paper · explained in 6 episodes
• Mapping Correctness — 4× in this paper
• Papers — 4× in this paper · explained in 3 episodes
• Source Prediction — 4× in this paper
• Supervised Fine-Tuning — 4× in this paper
• Conceptual Metaphor Theory — 3× in this paper
• Evidence Grounding — 3× in this paper · explained in 3 episodes
• Sentiment Classification — 3× in this paper
• Target Prediction — 3× in this paper
• Visual Grounding — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Chain-of-Thought Prompting — 2× in this paper · explained in 2 episodes
• Composition — 2× in this paper · explained in 2 episodes
• Granularity Mismatch — 2× in this paper · explained in 2 episodes
• Hallucination — 2× in this paper · explained in 4 episodes
• Multimodal Dataset — 2× in this paper · explained in 2 episodes
• Vision-language models — 2× in this paper · explained in 2 episodes
• Ablation Study — 1× in this paper · explained in 3 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Curriculum Learning — 1× in this paper · explained in 3 episodes
• Group Relative Policy Optimization — 1× in this paper
• Interpretability — 1× in this paper · explained in 15 episodes
• KL Regularization — 1× in this paper · explained in 2 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Localization — 1× in this paper · explained in 2 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Selectional Preference Violation — 1× in this paper
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 13 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Transformers — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 6 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Qwen3-VL Technical Report
• Kimi K2.5: Visual Agentic Intelligence
• GPT-4o System Card
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering