EviScene:超越「是否由 AI 生成」的智能體圖像事實性評估
EviScene: Beyond "Is It AI?" for Agentic Image Factuality Assessment
研究提出 EviScene,一個透過視覺檢查、外部檢索及證據分析,判斷圖像所描繪情況是否有事實支持的多模態 ReAct 智能體。研究亦推出專家審核的 EviLens 基準,收錄 10,174 張有支持或遭反駁的圖像,涵蓋 12 種事實錯誤類型。
Published on Oct 10
·
on Oct 14
Authors:
,
,
,
,
,
,
,
,
,
,
,
Abstract
Determining whether an image is AI-generated does not establish whether the situation it depicts is factually supported. We formulate Image Factuality Assessment: given an image and a generic verification instruction, a system returns a supported or refuted verdict with an evidence-grounded explanation. Without a supplied textual claim, the system must progressively refine factual questions during investigation and align external evidence with the specific situation depicted. We introduce EviLens, an expert-reviewed benchmark of 10,174 supported and refuted images from controlled construction and web collection, covering twelve factual error types and evaluating both verdict accuracy and evidence sufficiency. We develop EviScene, a multimodal ReAct agent that interleaves visual inspection, external retrieval, and evidence analysis, using new findings to refine its questions and revisit relevant image details. We train a compact policy with supervised fine-tuning on reviewed teacher trajectories, followed by privileged on-policy self-distillation applied to verified decisions from the policy's own investigations. On the 1,527-image test set, the trained Qwen3.5-9B agent achieves 79.05% balanced accuracy and a Strict Evidence Sufficiency Rate (SESR) of 52.26%, improving over the same-backbone base agent by 6.71 and 9.37 percentage points, respectively. Its SESR is the highest among the evaluated agents.Code, models, and data will be released at https://github.com/wangzian828/EVISCENE and https://huggingface.co/ZiAnwang/EviScene.
View arXiv page View PDF Add to collection
Get this paper in your agent:
hf papers read 2610.14609
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 1
Updated about 2 hours agoZiAnwang/EviScene
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.14609 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.14609 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co