paper-with-me

홈 › Papers

Can Multi-modal (reasoning) LLMs detect document manipulation?

2025-08-14 · Zisheng Liang, Kidus Zewde, Rudra Pratap Singh, Disha Patil, Zexi Chen, Jiayu Xue, Yao Yao, Yifei Chen, Qinzhe Liu, Simiao Ren arxiv

Document fraud poses a significant threat to industries reliant on secure and verifiable documentation, necessitating robust detection mechanisms. This study investigates the efficacy of state-of-the-art multi-modal large language models (LLMs)-including OpenAI O1, OpenAI 4o, Gemini Flash (thinking), Deepseek Janus, Grok, Llama 3.2 and 4, Qwen 2 and 2.5 VL, Mistral Pixtral, and Claude 3.5 and 3.7 Sonnet-in detecting fraudulent documents. We benchmark these models against each other and prior work on document fraud detection techniques using a standard dataset with real transactional documents. Through prompt optimization and detailed analysis of the models' reasoning processes, we evaluate their ability to identify subtle indicators of fraud, such as tampered text, misaligned formatting, and inconsistent transactional sums. Our results reveal that top-performing multi-modal LLMs demonstrate superior zero-shot generalization, outperforming conventional methods on out-of-distribution datasets, while several vision LLMs exhibit inconsistent or subpar performance. Notably, model size and advanced reasoning capabilities show limited correlation with detection accuracy, suggesting task-specific fine-tuning is critical. This study underscores the potential of multi-modal LLMs in enhancing document fraud detection systems and provides a foundation for future research into interpretable and scalable fraud mitigation strategies.

📄 PDF Abstract BibTeX arXiv:2508.11021

Code (0)

등록된 구현이 없습니다.

Tasks

Zero-shot GeneralizationFraud Detection

Similar Papers 제목 키워드 기반

Read and Think: An Efficient Step-wise Multimodal Language Model for Document Understanding and Reasoning

2024-02-26 · Jinxu Zhang

Understanding the contents of multimodal documents is essential to accurately extract relevant evidence and use it for reasoning. Existing document understanding models tend to generate answers with a single word or phra…

Data Augmentationdocument understandingLanguage ModelingLanguage Modelling+5

LED: A Benchmark for Evaluating Layout Error Detection in Document Analysis

2026-03-18 · Inbum Heo, Taewook Hwang, Jeesu Jung, Sangkeun Jung arxiv

Recent advances in Large Language Models (LLMs) and Large Multimodal Models (LMMs) have improved Document Layout Analysis (DLA), yet structural errors such as region merging, splitting, and omission remain persistent. Co…

Document Layout Analysis

FinMMDocR: Benchmarking Financial Multimodal Reasoning with Scenario Awareness, Document Understanding, and Multi-Step Computation

2025-12-31 · Zichen Tang, Haihong E, Rongjin Li, Jiacheng Liu 외 arxiv

We introduce FinMMDocR, a novel bilingual multimodal benchmark for evaluating multimodal large language models (MLLMs) on real-world financial numerical reasoning. Compared to existing benchmarks, our work delivers three…

Multimodal Reasoning

BRIDGE: Benchmark for multi-hop Reasoning In long multimodal Documents with Grounded Evidence

2026-03-09 · Biao Xiang, Soyeon Caren Han, Yihao Ding arxiv

Multi-hop question answering (QA) is widely used to evaluate the reasoning capabilities of large language models, yet most benchmarks focus on final answer correctness and overlook intermediate reasoning, especially in l…

Multi-hop Question Answering

ShredBench: Evaluating the Semantic Reasoning Capabilities of Multimodal LLMs in Document Reconstruction

2026-04-26 · Zichun Guo, Yuling Shi, Wenhao Zeng, Chao Hu 외 arxiv

Multimodal Large Language Models (MLLMs) have achieved remarkable performance in Visually Rich Document Understanding (VRDU) tasks, but their capabilities are mainly evaluated on pristine, well-structured document images…