AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

VAGUE: Visual Contexts Clarify Ambiguous Expressions

Heejeong Nam, Jinwoo Ahn, Keummin Ka, Jiwan Chung, Youngjae Yu

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Chain-of-thought multimodal reasoning · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add raw image input (VLM) instead of text only (LM) (ablation)Qwen2.5-VL-Instruct (7B) · VAGUE-VCRaccuracy (%): 11.1 -> 46.8Improved
add image captions (SM) instead of text only (LM) (ablation)GPT-4o · VAGUE-VCRaccuracy (%): 46.4 -> 69.5Improved
give raw images (VLM) instead of captions (SM) to proprietary models (ablation)GPT-4o · VAGUE-VCRaccuracy (%): 69.5 -> 65.1Hurt
give raw images (VLM) instead of captions (SM) to open-source models (ablation)Qwen2.5-VL-Instruct (72B) · VAGUE-VCRaccuracy (%): 55.6 -> 74.2Improved
add image or caption input for Ovis2 (16B) (ablation)Ovis2 (16B) · VAGUE-VCRaccuracy (%): 21.9 -> 24.5No clear effect
add zero-shot chain-of-thought prompting to raw image input (ablation)GPT-4o · VAGUE (CoT subset)accuracy (%): 64.6 -> 66.4Improved
add zero-shot chain-of-thought prompting to raw image input (ablation)Gemini-1.5-Pro · VAGUE (CoT subset)accuracy (%): 60.6 -> 64.4Improved
add zero-shot chain-of-thought prompting to caption input (ablation)GPT-4o and Gemini-1.5-Pro · VAGUE (CoT subset)accuracy (%): GPT-4o 68.9 -> 69.5; Gemini 61.8 -> 61.0No clear effect
compare best model with human on 400-question subsetVLMs · VAGUE 400-question subsetaccuracy (%): Human 94.0 vs Qwen2.5-VL-72B 72.3Hurt
model errors by type (superficial understanding vs scene hallucination)VLMs · VAGUE 400-question subsetincorrect choice counts: SU 183 vs FS 43 vs NE 10 (LLaVA-Onevision 7B)Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy