Zhihui/Vl-RewardBench

VLRewardBench是一个综合基准测试，旨在评估视觉-语言生成奖励模型（VL-GenRMs）在视觉感知、幻觉检测和推理任务中的表现。该数据集包含1,250个高质量示例，专门用于探测模型的局限性。每个实例由多模态查询组成，涵盖三个关键领域：来自真实用户的一般多模态查询、视觉幻觉检测任务以及多模态知识和数学推理。数据集的结构包括多个关键字段，如id、query、image、response等。数据集的使用仅限于研究目的，旨在评估和改进视觉-语言奖励模型，研究模型在视觉感知和推理方面的局限性，以及开发更好的多模态AI系统。

VLRewardBench is a comprehensive benchmark designed to evaluate vision-language generative reward models (VL-GenRMs) across visual perception, hallucination detection, and reasoning tasks. The benchmark contains 1,250 high-quality examples specifically curated to probe model limitations. Each instance consists of multimodal queries spanning three key domains: general multimodal queries from real users, visual hallucination detection tasks, and multimodal knowledge and mathematical reasoning. The dataset structure includes key fields such as id, query, image, response, etc. The dataset is intended for research use only, specifically for evaluating and improving vision-language reward models, studying model limitations in visual perception and reasoning, and developing better multimodal AI systems.