Seeing Before Reasoning: A Unified Framework for Generalizable and Explainable Fake Image Detection

ICLR 2026 Conference Submission80 Authors

Keywords: AI-Generated Image Detection, MLLM, Media Forensics

TL;DR: We propose a unified MLLM-based framework that simultaneously perceives low-level artifacts and reasons dialectically about high-level plausibility, without reliance on external detectors.

Abstract:

Detecting AI-generated images with multimodal large language models (MLLMs) has gained increasing attention, due to their rich world knowledge, common-sense reasoning, and potential for explainability.
However, naively applying those MLLMs for detection often leads to suboptimal performance.
We argue that the root of this failure lies in a fundamental mismatch: *MLLMs are asked to reason about fakes before they can truly see them.*
First, **they do not really see**: existing MLLMs' vision encoders are primarily optimized for semantic-oriented recognition rather than the perception of low-level signals, leaving them insensitive to subtle forgery traces. Without access to reliable perceptual evidence, the model grounds its judgment on incomplete and limited visual observations.
Second, existing finetuning data for detection typically uses narrow, instruction-style formats, which diverge sharply from the diverse, heterogeneous distributions seen in pretraining.
In the absence of meaningful visual cues, the model therefore exploits these linguistic shortcuts, resulting in catastrophic forgetting of pretrained knowledge (even the basic dialogue capabilities).
In response, we advocate for a new paradigm: *seeing before reasoning*. We propose that MLLMs should first be trained to perceive artifacts—strengthening their artifact-aware visual perception—so that subsequent reasoning is grounded in actual observations.
We therefore propose **Forensic-Chat**, a generalizable, explainable, and still-conversational (for multi-round dialogue) assistant for fake image detection.
Specifically, we first refine the vision encoder only via self-reconstruction while freezing the LLM, sensitizing it to artifacts without sacrificing pretrained knowledge (Stage 1).
Then, we construct a multi-round dialogue finetuning data for detection, which is designed to progressively guide the model from artifact perception to common-sense reflection, enabling dialectical reasoning about *why an image is fake* and *what a real version should look like* (Stage 2).
We also propose **ExplainFake-Bench**, a benchmark tailored for the evaluation of the MLLM's explainability for image forensics from five key aspects.
Extensive experiments show the superiority of generalization and genuinely reliable explainability.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 80