paper-with-me

Papers

MagiC: Evaluating Multimodal Cognition Toward Grounded Visual Reasoning

2025-07-09 · Chengfei Wu, Ronald Seoh, Bingxuan Li, Liqiang Zhang, Fengrong Han, Dan Goldwasser

Recent advances in large vision-language models have led to impressive performance in visual question answering and multimodal reasoning. However, it remains unclear whether these models genuinely perform grounded visual reasoning or rely on superficial patterns and dataset biases. In this work, we introduce MagiC, a comprehensive benchmark designed to evaluate grounded multimodal cognition, assessing not only answer accuracy but also the quality of step-by-step reasoning and its alignment with relevant visual evidence. Our benchmark includes approximately 5,500 weakly supervised QA examples generated from strong model outputs and 900 human-curated examples with fine-grained annotations, including answers, rationales, and bounding box groundings. We evaluate 15 vision-language models ranging from 7B to 70B parameters across four dimensions: final answer correctness, reasoning validity, grounding fidelity, and self-correction ability. MagiC further includes diagnostic settings to probe model robustness under adversarial visual cues and assess their capacity for introspective error correction. We introduce new metrics such as MagiScore and StepSense, and provide comprehensive analyses that reveal key limitations and opportunities in current approaches to grounded visual reasoning.

📄 PDF Abstract BibTeX arXiv:2507.07297

Code (0)

등록된 구현이 없습니다.

Tasks

DiagnosticMultimodal ReasoningQuestion AnsweringVisual Question AnsweringVisual Reasoning

Similar Papers 제목 키워드 기반

Language Models Can See: Plugging Visual Controls in Text Generation

2022-05-05 · Yixuan Su, Tian Lan, Yahui Liu, Fangyu Liu 외

Generative language models (LMs) such as GPT-2/3 can be prompted to generate text with remarkable quality. While they are designed for text-prompted generation, it remains an open question how the generation process coul…

Image CaptioningImage-text matchingOpen-Ended Question AnsweringStory Generation+2

MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering

2025-03-24 · Shuo Yang, Siwen Luo, Soyeon Caren Han, Eduard Hovy

Visual Question Answering (VQA) requires reasoning across visual and textual modalities, yet Large Vision-Language Models (LVLMs) often lack integrated commonsense knowledge, limiting their robustness in real-world scena…

Graph Neural NetworkQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

ChinaHeritaQA: A Culturally-Grounded Visual Question Answering Dataset for World Heritage Sites in China

2026-06-08 · Yi Zhang, Bolei Ma, Yong Cao, Chengyan Wu 외 arxiv

We introduce ChinaHeritaQA, a multimodal benchmark dataset for evaluating the cultural reasoning abilities of vision-language models (VLMs) on UNESCO World Heritage sites in China. The dataset comprises 2,279 in-the-wild…

Visual Question Answering

ImageEval 2026: Culturally Grounded Arabic Multimodal Evaluation

2026-08-31 · Samir Abdaljalil, Hunzalah Hassan Bhatti, Ahlam Bashiti, Farina Amir 외 arxiv

We present an overview of the ImageEval 2026 shared task on culturally grounded Arabic multimodal evaluation. It includes two tasks: (i) AynVQA, covering spoken visual question answering and image-grounded hallucination …

Visual Question AnsweringText-to-Image Generation

MAGIC: Multimodal Alignment & Grounding-aware Instruction Coreset for Vision-Language Models

2026-05-25 · Shristi Das Biswas, Kaushik Roy arxiv

Instruction tuning of large vision-language models (LVLMs) increasingly depends on massive multimodal corpora, yet these datasets contain samples with substantial redundancy, low visual dependency, and highly imbalanced …

Multimodal Reasoning