paper-with-me

홈 › Papers

M$^3$R-Bench: A Unified Benchmark for Evidence-Grounded Multimodal Metaphor Understanding

2026-08-06 · Hong Jiang, Junnan Zhu, Jingwang Huang, Xiao Sun, Yuming Yang, Jiang Zhong, Ruirui Chen, Jingman Shi, Hao Wu, Nayu Liu, Xinyi Jiang, Kaiwen Wei arxiv

Metaphor enables the understanding of abstract concepts through cross-domain mappings while conveying affective attitudes. In multimodal scenarios, visual and textual information jointly construct Target--Source mappings, requiring both conceptual understanding and cross-modal reasoning. However, existing benchmarks mainly evaluate metaphor understanding through isolated subtasks and lack evidence-grounded explanations, making it difficult to assess whether models establish mappings grounded in visual and textual cues.To address these limitations, we introduce M$^3$R-Bench, a unified and evidence-grounded benchmark containing 1,000 image--text instances with human-verified annotations. Guided by Conceptual Metaphor Theory and theories of nonliteral language understanding, M$^3$R-Bench provides joint annotations for metaphor occurrence, Target--Source mapping, sentiment, and stage-wise explanations following ``evidence identification--mapping establishment--sentiment inference.''Evaluations on M$^3$R-Bench reveal that existing models often overlook visual evidence, rely on superficial textual cues, and produce inaccurate Target--Source mappings, exposing a cross-modal evidence--mapping mismatch. To address this mismatch, we propose M$^3$R-Reasoner, which combines curriculum-based reasoning supervision with task-aware reinforcement learning to align model reasoning with metaphor interpretation. Experiments show that, with only an 8B-parameter backbone, M$^3$R-Reasoner outperforms larger proprietary MLLMs across four unified-task metrics and improves Visual Evidence and Sentiment Justification scores over GPT-5.5 by 28.45 and 30.11 points, respectively, while surpassing Claude-Sonnet-4.6 by 8.00 points in mean rubric score. The dataset and code are available at https://github.com/hongshi4/M3R-Bench.

📄 PDF Abstract BibTeX arXiv:2608.05817

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents

2026-01-18 · Peizhou Huang, Zixuan Zhong, Zhongwei Wan, Donghao Zhou 외 arxiv

Deep Research Agents (DRAs) generate citation-rich reports via multi-step search and synthesis, yet existing benchmarks mainly target text-only settings or short-form multimodal QA, missing end-to-end multimodal evidence…

Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis

2026-03-31 · Shuang Chen, Quanxin Shou, Hangting Chen, Yucheng Zhou 외 arxiv

Unified multimodal models provide a natural and promising architecture for understanding diverse and complex real-world knowledge while generating high-quality images. However, they still rely primarily on frozen paramet…

Image Generation

The Ebb and Flow of Multimodal Focus: Scheduling Visual Relay Windows for Grounded VLM Reasoning

2026-07-13 · Wencheng Ye, Yi Bin, Yujuan Ding, Hongye Fang 외 arxiv

Vision-language models increasingly succeed on multimodal reasoning benchmarks, yet their visual evidence often becomes unstable once it enters the language stack, weakening evidence-grounded reasoning. To understand thi…

Multimodal Reasoning

RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild

2025-12-28 · Danni Xu, Shaojing Fan, Harry Cheng, Mohan Kankanhalli arxiv

Multimodal misinformation increasingly leverages visual persuasion, where repurposed or manipulated images strengthen misleading text. We introduce RW-Post, a post-aligned text--image benchmark for real-world multimodal …

Visual Grounding

RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild

2026-05-11 · Danni Xu, Shaojing Fan, Harry Cheng, Mohan Kankanhalli arxiv

Multimodal misinformation increasingly leverages visual persuasion, where repurposed or manipulated images strengthen misleading text. We introduce \textbf{RW-Post}, a post-aligned \textbf{text--image benchmark} for real…

Visual Grounding