# From Sharp Eyes to Expert Mind: Internalizing Expert Knowledge in MLLMs for Tampered Text Detection

arXiv: https://arxiv.org/abs/2609.36145 · HTML: https://mlsanity.com/paper/2609.36145/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 55 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 30 of 35)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Character Region Awareness for Text Detection](https://mlsanity.com/paper/1904.01941/) (2019)
- [Learning Rich Features for Image Manipulation Detection](https://mlsanity.com/paper/1805.04953/) (2018)
- [UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model](https://mlsanity.com/paper/2310.05126/) (2023)
- [PaddleOCR 3.0 Technical Report](https://mlsanity.com/paper/2507.05595/) (2025)
- [Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model](https://mlsanity.com/paper/2510.12276/) (2025)
- [PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localization](https://mlsanity.com/paper/2103.10596/) (2021)
- [TruFor: Leveraging all-round clues for trustworthy image forgery detection and localization](https://mlsanity.com/paper/2212.10957/) (2022)
- [Common Sense Reasoning for Deepfake Detection](https://mlsanity.com/paper/2402.00126/) (2024)
- [FFAA: Multimodal Large Language Model based Explainable Open-World Face Forgery Analysis Assistant](https://mlsanity.com/paper/2408.10072/) (2024)
- [IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformer](https://mlsanity.com/paper/2307.14863/) (2023)
- [IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization](https://mlsanity.com/paper/2406.10580/) (2024)
- [Visual Representation Alignment for Multimodal Large Language Models](https://mlsanity.com/paper/2509.07979/) (2025)
- [FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models](https://mlsanity.com/paper/2404.13306/) (2024)
- [X2-DFD: A framework for eXplainable and eXtendable Deepfake Detection](https://mlsanity.com/paper/2410.06126/) (2024)
- [Mesoscopic Insights: Orchestrating Multi-scale & Hybrid Architecture for Image Manipulation Localization](https://mlsanity.com/paper/2412.13753/) (2024)
- [AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Models](https://mlsanity.com/paper/2507.02664/) (2025)
- [Can We Get Rid of Handcrafted Feature Extractors? SparseViT: Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization through Spare-Coding Transformer](https://mlsanity.com/paper/2412.14598/) (2024)
- [LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding](https://mlsanity.com/paper/2403.14252/) (2024)
- [ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization](https://mlsanity.com/paper/2505.11003/) (2025)
- [Revisiting Tampered Scene Text Detection in the Era of Generative AI](https://mlsanity.com/paper/2407.21422/) (2024)
- [Toward Real Text Manipulation Detection: New Dataset and New Solution](https://mlsanity.com/paper/2312.06934/) (2023)
- [Seeing Before Reasoning: A Unified Framework for Generalizable and Explainable Fake Image Detection](https://mlsanity.com/paper/2509.25502/) (2025)
- [Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning](https://mlsanity.com/paper/2504.07198/) (2025)

## Abstract (arXiv)

Tampered Text Detection (TTD) is essential for safeguarding document authenticity in security-critical workflows. Existing expert models are effective at capturing subtle manipulation traces but often generalize poorly across diverse document domains, while Multimodal Large Language Models (MLLMs) offer stronger semantic understanding and transferability yet remain insensitive to fine-grained forensic artifacts. This complementarity motivates us to investigate how expert forensic perception can be internalized into an MLLM rather than merely accessed through an external module. We identify a fundamental Double Mismatch that hinders this goal: a Spatial Precision Mismatch between coarse visual tokens and tiny tampered regions, and a Perceptual Granularity Mismatch between semantics-oriented pre-training and low-level forensic perception. To address these challenges, we propose Expert Knowledge Internalization (EKI), a progressive two-stage framework that transfers forensic expertise into the MLLM itself. In Stage 1, Text-Focused and Image-Focused strategies establish precise spatial focus on small text regions. In Stage 2, the proposed Forensic-General Representation Alignment (FGRA) loss aligns shallow LLM representations with those of a pre-trained forensic expert, enabling the model to acquire fine-grained artifact perception before such cues are diluted by deeper semantic abstraction. Extensive experiments on multiple in-domain and cross-domain benchmarks demonstrate that EKI achieves state-of-the-art performance and stronger generalization than existing expert-model-based and MLLM-based methods. Moreover, the expert is required only during training, allowing the resulting MLLM to maintain inference efficiency nearly identical to the vanilla model without relying on any external expert at inference.