Prefill-Guided Thinking for zero-shot detection of AI-generated images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kachwala, Zoher, Singh, Danishjeet, Yang, Danielle, Menczer, Filippo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915754111139840
author Kachwala, Zoher
Singh, Danishjeet
Yang, Danielle
Menczer, Filippo
author_facet Kachwala, Zoher
Singh, Danishjeet
Yang, Danielle
Menczer, Filippo
contents Traditional supervised methods for detecting AI-generated images depend on large, curated datasets for training and fail to generalize to novel, out-of-domain image generators. As an alternative, we explore pre-trained Vision-Language Models (VLMs) for zero-shot detection of AI-generated images. We evaluate VLM performance on three diverse benchmarks encompassing synthetic images of human faces, objects, and animals produced by 16 different state-of-the-art image generators. While off-the-shelf VLMs perform poorly on these datasets, we find that prefilling responses effectively guides their reasoning -- a method we call Prefill-Guided Thinking (PGT). In particular, prefilling a VLM response with the phrase "Let's examine the style and the synthesis artifacts" improves the Macro F1 scores of three widely used open-source VLMs by up to 24%. We analyze this improvement in detection by tracking answer confidence during response generation. For some models, prefills counteract early overconfidence -- akin to mitigating the Dunning-Kruger effect -- leading to better detection performance.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11031
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prefill-Guided Thinking for zero-shot detection of AI-generated images
Kachwala, Zoher
Singh, Danishjeet
Yang, Danielle
Menczer, Filippo
Machine Learning
Artificial Intelligence
Computation and Language
Traditional supervised methods for detecting AI-generated images depend on large, curated datasets for training and fail to generalize to novel, out-of-domain image generators. As an alternative, we explore pre-trained Vision-Language Models (VLMs) for zero-shot detection of AI-generated images. We evaluate VLM performance on three diverse benchmarks encompassing synthetic images of human faces, objects, and animals produced by 16 different state-of-the-art image generators. While off-the-shelf VLMs perform poorly on these datasets, we find that prefilling responses effectively guides their reasoning -- a method we call Prefill-Guided Thinking (PGT). In particular, prefilling a VLM response with the phrase "Let's examine the style and the synthesis artifacts" improves the Macro F1 scores of three widely used open-source VLMs by up to 24%. We analyze this improvement in detection by tracking answer confidence during response generation. For some models, prefills counteract early overconfidence -- akin to mitigating the Dunning-Kruger effect -- leading to better detection performance.
title Prefill-Guided Thinking for zero-shot detection of AI-generated images
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2506.11031