Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning
Large Vision-Language Models (LVLMs) have demonstrated remarkable performance across diverse tasks. Despite great success, recent studies show that LVLMs encounter substantial limitations when engaging with visual graphs. To study the reason behind these limitations, we propose VGCure, a comprehensive benchmark covering 22 tasks for examining the fundamental graph understanding and reasoning capacities of LVLMs. Extensive evaluations conducted on 14 LVLMs reveal that LVLMs are weak in basic graph understanding and reasoning tasks, particularly those concerning relational or structurally complex information. Based on this observation, we propose a structure-aware fine-tuning framework to enhance LVLMs with structure learning abilities through 3 self-supervised learning tasks. Experiments validate the effectiveness of our method in improving LVLMs' zero-shot performance on fundamental graph learning tasks, as well as enhancing the robustness of LVLMs against complex visual graphs.
Code (1)
Tasks
BenchmarkingGraph LearningSelf-Supervised LearningSimilar Papers 제목 키워드 기반
SeePhys: Does Seeing Help Thinking? -- Benchmarking Vision-Based Physics Reasoning
We present SeePhys, a large-scale multimodal benchmark for LLM reasoning grounded in physics questions ranging from middle school to PhD qualifying exams. The benchmark covers 7 fundamental domains spanning the physics d…
BenchmarkingVisual ReasoningVisFactor: Benchmarking Fundamental Visual Cognition in Multimodal Large Language Models
Multimodal Large Language Models (MLLMs) have demonstrated remarkable advancements in multimodal understanding; however, their fundamental visual cognitive abilities remain largely underexplored. To bridge this gap, we i…
BenchmarkingSpatial ReasoningVisual ReasoningSVHalluc: Benchmarking Speech-Vision Hallucination in Audio-Visual Large Language Models
Despite the success of audio-visual large-language models (LLMs), they can produce plausible but ungrounded outputs, termed hallucination. Existing benchmarks focus on environmental sounds (e.g., dog barking) to indicate…
AutoViVQA: A Large-Scale Automatically Constructed Dataset for Vietnamese Visual Question Answering
Visual Question Answering (VQA) is a fundamental multimodal task that requires models to jointly understand visual and textual information. Early VQA systems relied heavily on language biases, motivating subsequent work …
Visual Question AnsweringRepresentation LearningMachine TranslationImage CaptioningBenchmarking Direct Preference Optimization for Medical Large Vision-Language Models
Large Vision-Language Models (LVLMs) hold significant promise for medical applications, yet their deployment is often constrained by insufficient alignment and reliability. While Direct Preference Optimization (DPO) has …