Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos

Hugging Face Daily Papers Papers

Summary

Artifact-Bench is a comprehensive benchmark that evaluates multimodal large language models on detecting and analyzing artifacts in AI-generated videos, revealing significant limitations and misalignment with human perception.

Recent video generative models have greatly improved the realism of AI-generated videos, yet their outputs still exhibit artifacts such as temporal inconsistencies, structural distortions, and semantic incoherence. While Multimodal Large Language Models (MLLMs) show strong visual understanding capabilities, their ability to perceive and reason about such artifacts remains unclear. Existing benchmarks often lack systematic evaluation of artifact-aware perception and fine-grained diagnostic reasoning, especially across diverse AI-generated video domains beyond photorealistic content. To address this gap, we introduce Artifact-Bench, a comprehensive benchmark for evaluating MLLMs on AI-generated video artifact detection and analysis. We first establish a three-level hierarchical taxonomy of realism artifacts, covering photorealistic, animated, and CG-style videos. Based on this taxonomy, Artifact-Bench defines three complementary tasks: real vs. AI-generated video classification, pairwise realism comparison, and fine-grained artifact identification. Experiments on 19 leading MLLMs reveal substantial limitations in artifact perception and reasoning, with many models approaching random or even below-random performance in challenging settings. We further observe significant misalignment between MLLM judgments and human perceptual preferences, highlighting their limited reliability as general evaluators for AI-generated video realism.
Original Article
View Cached Full Text

Cached at: 05/20/26, 02:36 AM

Paper page - Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos

Source: https://huggingface.co/papers/2605.18984 Published on May 18

#1 Paper of the day Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Artifact-Bench evaluates multimodal large language models’ capability to detect and analyze artifacts in AI-generated videos, revealing significant limitations in artifact perception and reasoning.

Recent video generative models have greatly improved the realism ofAI-generated videos, yet their outputs still exhibit artifacts such as temporal inconsistencies, structural distortions, and semantic incoherence. WhileMultimodal Large Language Models(MLLMs) show strongvisual understandingcapabilities, their ability to perceive and reason about such artifacts remains unclear. Existing benchmarks often lack systematic evaluation of artifact-aware perception and fine-graineddiagnostic reasoning, especially across diverseAI-generated videodomains beyond photorealistic content. To address this gap, we introduce Artifact-Bench, a comprehensive benchmark for evaluating MLLMs onAI-generated videoartifact detectionand analysis. We first establish a three-level hierarchical taxonomy ofrealism artifacts, covering photorealistic, animated, and CG-style videos. Based on this taxonomy, Artifact-Bench defines three complementary tasks: real vs.AI-generated videoclassification, pairwise realism comparison, andfine-grained artifact identification. Experiments on 19 leading MLLMs reveal substantial limitations in artifact perception and reasoning, with many models approaching random or even below-random performance in challenging settings. We further observe significant misalignment between MLLM judgments and human perceptual preferences, highlighting their limited reliability as general evaluators forAI-generated videorealism.

View arXiv pageView PDFGitHub1Add to collection

Get this paper in your agent:

hf papers read 2605\.18984

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.18984 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.18984 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.18984 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models

Hugging Face Daily Papers

PerceptionBench is a benchmark designed to evaluate atomic visual perception capabilities of Multimodal Large Language Models (MLLMs), using a bottom-up taxonomy of ten atomic perceptual capabilities. Results across 16 frontier MLLMs show no model reaches 60% accuracy, indicating visual perception remains largely unsolved.

Zero-Shot Mission-Level Evaluation for Aerial MLLM Agents

arXiv cs.CL

MissionBench is a new benchmark for evaluating multimodal large language models (MLLMs) on long-horizon embodied tasks in aerial 3D environments, revealing that even the best models succeed on fewer than 35% of missions compared to 84.4% human performance.