WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences

• URL: http://arxiv.org/abs/2406.11069v1
• Date: Sun, 16 Jun 2024 20:53:25 GMT
• Title: WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences
• Authors: Yujie Lu, Dongfu Jiang, Wenhu Chen, William Yang Wang, Yejin Choi, Bill Yuchen Lin,
• Abstract summary: We launch WildVision-Arena (WV-Arena), an online platform that collects human preferences to evaluate vision-language models (VLMs) WV-Bench uses GPT-4 as the judge to compare each VLM with Claude-3-Sonnet, achieving a Spearman correlation of 0.94 with the WV-Arena Elo. Our comprehensive analysis of 20K real-world interactions reveals important insights into the failure cases of top-performing VLMs.
• Score: 122.87483437694706
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent breakthroughs in vision-language models (VLMs) emphasize the necessity of benchmarking human preferences in real-world multimodal interactions. To address this gap, we launched WildVision-Arena (WV-Arena), an online platform that collects human preferences to evaluate VLMs. We curated WV-Bench by selecting 500 high-quality samples from 8,000 user submissions in WV-Arena. WV-Bench uses GPT-4 as the judge to compare each VLM with Claude-3-Sonnet, achieving a Spearman correlation of 0.94 with the WV-Arena Elo. This significantly outperforms other benchmarks like MMVet, MMMU, and MMStar. Our comprehensive analysis of 20K real-world interactions reveals important insights into the failure cases of top-performing VLMs. For example, we find that although GPT-4V surpasses many other models like Reka-Flash, Opus, and Yi-VL-Plus in simple visual recognition and reasoning tasks, it still faces challenges with subtle contextual cues, spatial reasoning, visual imagination, and expert domain knowledge. Additionally, current VLMs exhibit issues with hallucinations and safety when intentionally provoked. We are releasing our chat and feedback data to further advance research in the field of VLMs.

Related papers

• Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Models [82.92771279118888]
  We introduce Multimodal RewardBench, an expert-annotated benchmark for evaluating multimodal reward models. Our dataset comprises 5,211 annotated (prompt, chosen response, rejected response) triplets collected from various vision-language models. We find that even the top-performing models, Gemini 1.5 Pro and Claude 3.5 Sonnet, achieve only 72% overall accuracy.
  arXiv  Detail & Related papers  (2025-02-20T01:48:13Z)
• Can LVLMs and Automatic Metrics Capture Underlying Preferences of Blind and Low-Vision Individuals for Navigational Aid? [16.31494394717809]
  Blind and Low-Vision (BLV) people need assistance understanding their surroundings, especially in unfamiliar environments. It has yet been studied preferences of BLV users on diverse types/styles of responses from Large Vision-Language Models (LVLMs) We first construct Eye4B dataset, consisting of human-validated 1.1k curated outdoor/indoor scenes with 5-10 relevant requests per scene. Then, we conduct an in-depth user study with eight BLV users to evaluate their preferences on six LVLMs from five perspectives: Afraidness, Nonactionability, Sufficiency, and Conciseness.
  arXiv  Detail & Related papers  (2025-02-15T10:17:52Z)
• Probing Visual Language Priors in VLMs [51.016683265437536]
  We introduce ViLP, a benchmark featuring deliberately out-of-distribution images. Each question in ViLP is coupled with three potential answers and three corresponding images. We propose a self-improving framework in which models generate new VQA data, then apply pixel-level and semantic corruptions to form "good-bad" image pairs for self-training.
  arXiv  Detail & Related papers  (2024-12-31T17:54:29Z)
• VisionArena: 230K Real World User-VLM Conversations with Preference Labels [68.11192349083832]
  VisionArena is a dataset of 230K real-world conversations between users and vision-language models (VLMs) Our dataset spans 73K unique users, 45 VLMs, and 138 languages. We find open-ended tasks like captioning and humor are highly style-dependent, and current VLMs struggle with spatial reasoning and planning tasks.
  arXiv  Detail & Related papers  (2024-12-11T18:59:46Z)
• Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension [95.63899307791665]
  Vision Value Model (VisVM) can guide VLM inference-time search to generate responses with better visual comprehension. In this paper, we present VisVM that can guide VLM inference-time search to generate responses with better visual comprehension.
  arXiv  Detail & Related papers  (2024-12-04T20:35:07Z)
• VHELM: A Holistic Evaluation of Vision Language Models [75.88987277686914]
  We present the Holistic Evaluation of Vision Language Models (VHELM) VHELM aggregates various datasets to cover one or more of the 9 aspects: visual perception, knowledge, reasoning, bias, fairness, multilinguality, robustness, toxicity, and safety. Our framework is designed to be lightweight and automatic so that evaluation runs are cheap and fast.
  arXiv  Detail & Related papers  (2024-10-09T17:46:34Z)
• Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models [61.899791071654654]
  We introduce a benchmark, Q-Spatial Bench, with 271 questions across five categories designed for quantitative spatial reasoning. We investigate the performance of state-of-the-art vision-language models (VLMs) on this task. We develop a zero-shot prompting technique, SpatialPrompt, that encourages VLMs to answer quantitative spatial questions using reference objects as visual cues.
  arXiv  Detail & Related papers  (2024-09-15T16:45:42Z)
• BEAF: Observing BEfore-AFter Changes to Evaluate Hallucination in Vision-language Models [20.697019266074747]
  Vision language models (VLMs) perceive the world through a combination of a visual encoder and a large language model (LLM) Recent studies show that VLMs are vulnerable to hallucination. We introduce new metrics: True Understanding (TU), IGnorance (IG), StuBbornness (SB), and InDecision (ID)
  arXiv  Detail & Related papers  (2024-07-18T12:11:12Z)
• TopViewRS: Vision-Language Models as Top-View Spatial Reasoners [38.406430696146714]
  Top-view perspective denotes a typical way in which humans read and reason over different types of maps. We introduce the TopViewRS dataset, consisting of 11,384 multiple-choice questions with either realistic or semantic top-view map as visual input. We then use it to study and evaluate VLMs across 4 perception and reasoning tasks with different levels of complexity.
  arXiv  Detail & Related papers  (2024-06-04T17:55:43Z)
• RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness [94.03511733306296]
  We introduce RLAIF-V, a framework that aligns MLLMs in a fully open-source paradigm for super GPT-4V trustworthiness. RLAIF-V maximally exploits the open-source feedback from two perspectives, including high-quality feedback data and online feedback learning algorithm. Experiments show that RLAIF-V substantially enhances the trustworthiness of models without sacrificing performance on other tasks.
  arXiv  Detail & Related papers  (2024-05-27T14:37:01Z)
• AVIBench: Towards Evaluating the Robustness of Large Vision-Language Model on Adversarial Visual-Instructions [52.9787902653558]
  Large Vision-Language Models (LVLMs) have shown significant progress in well responding to visual-instructions from users. Despite the critical importance of LVLMs' robustness against such threats, current research in this area remains limited. We introduce AVIBench, a framework designed to analyze the robustness of LVLMs when facing various adversarial visual-instructions.
  arXiv  Detail & Related papers  (2024-03-14T12:51:07Z)
• GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action Recognition [48.686183248092476]
  GPT4Ego is a straightforward yet remarkably potent VLM framework for ZS-EAR. We show GPT4Ego significantly outperforms existing VLMs on three large-scale egocentric video benchmarks.
  arXiv  Detail & Related papers  (2024-01-18T15:04:46Z)
• Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation [31.062433484245684]
  We train Prometheus-Vision, the first open-source VLM evaluator model that can understand the user-defined score criteria during evaluation. Prometheus-Vision shows the highest Pearson correlation with human evaluators and GPT-4V among open-source models.
  arXiv  Detail & Related papers  (2024-01-12T14:19:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.