AI-generated text detectors have become essential tools for maintaining content authenticity, yet their robustness against evasion attacks remains questionable. We present PDFuzz, a novel attack that exploits the discrepancy between visual text layout and extraction order in PDF documents. Our method preserves exact textual content while manipulating character positioning to scramble extraction sequences. We evaluate this approach against the ArguGPT detector using a dataset of human and AI-generated text. Our results demonstrate complete evasion: detector performance drops from (93.6 $\pm$ 1.4) % accuracy and 0.938 $\pm$ 0.014 F1 score to random-level performance ((50.4 $\pm$ 3.2) % accuracy, 0.0 F1 score) while maintaining perfect visual fidelity. Our work reveals a vulnerability in current detection systems that is inherent to PDF document structures and underscores the need for implementing sturdy safeguards against such attacks. We make our code publicly available at https://github.com/ACMCMC/PDFuzz.

Information extraction (IE) from Visually Rich Documents (VRDs) containing layout features along with text is a critical and well-studied task. Specialized non-LLM NLP-based solutions typically involve training models using both textual and geometric information to label sequences/tokens as named entities or answers to specific questions. However, these approaches lack reasoning, are not able to infer values not explicitly present in documents, and do not generalize well to new formats. Generative LLM-based approaches proposed recently are capable of reasoning, but struggle to comprehend clues from document layout especially in previously unseen document formats, and do not show competitive performance in heterogeneous VRD benchmark datasets. In this paper, we propose BLOCKIE, a novel LLM-based approach that organizes VRDs into localized, reusable semantic textual segments called $\textit{semantic blocks}$, which are processed independently. Through focused and more generalizable reasoning,our approach outperforms the state-of-the-art on public VRD benchmarks by 1-3% in F1 scores, is resilient to document formats previously not encountered and shows abilities to correctly extract information not explicitly present in documents.

Table recognition is using the computer to automatically understand the table, to detect the position of the table from the document or picture, and to correctly extract and identify the internal structure and content of the table. After earlier mainstream approaches based on heuristic rules and machine learning, the development of deep learning techniques has brought a new paradigm to this field. This review mainly discusses the table recognition problem from five aspects. The first part introduces data sets, benchmarks, and commonly used evaluation indicators. This section selects representative data sets, benchmarks, and evaluation indicators that are frequently used by researchers. The second part introduces the table recognition model. This survey introduces the development of the table recognition model, especially the table recognition model based on deep learning. It is generally accepted that table recognition is divided into two stages: table detection and table structure recognition. This section introduces the models that follow this paradigm (TD and TSR). The third part is the End-to-End method, this section introduces some scholars' attempts to use an end-to-end approach to solve the table recognition problem once and for all and the part are Data-centric methods, such as data augmentation, aligning benchmarks, and other methods. The fourth part is the data-centric approach, such as data enhancement, alignment benchmark, and so on. The fifth part summarizes and compares the experimental data in the field of form recognition, and analyzes the mainstream and more advantageous methods. Finally, this paper also discusses the possible development direction and trend of form processing in the future, to provide some ideas for researchers in the field of table recognition. (Resource will be released at https://github.com/Wa1den-jy/Topic-on-Table-Recognition .)

The surge of pre-training has witnessed the rapid development of document understanding recently. Pre-training and fine-tuning framework has been effectively used to tackle texts in various formats, including plain texts, document texts, and web texts. Despite achieving promising performance, existing pre-trained models usually target one specific document format at one time, making it difficult to combine knowledge from multiple document formats. To address this, we propose XDoc, a unified pre-trained model which deals with different document formats in a single model. For parameter efficiency, we share backbone parameters for different formats such as the word embedding layer and the Transformer layers. Meanwhile, we introduce adaptive layers with lightweight parameters to enhance the distinction across different formats. Experimental results have demonstrated that with only 36.7% parameters, XDoc achieves comparable or even better performance on a variety of downstream tasks compared with the individual pre-trained models, which is cost effective for real-world deployment. The code and pre-trained models will be publicly available at \url{https://aka.ms/xdoc}.

Extraction of categorised named entities from text is a complex task given the availability of a variety of Named Entity Recognition (NER) models and the unstructured information encoded in different source document formats. Processing the documents to extract text, identifying suitable NER models for a task, and obtaining statistical information is important in data analysis to make informed decisions. This paper presents TNNT, a toolkit that automates the extraction of categorised named entities from unstructured information encoded in source documents, using diverse state-of-the-art Natural Language Processing (NLP) tools and NER models. TNNT integrates 21 different NER models as part of a Knowledge Graph Construction Pipeline (KGCP) that takes a document set as input and processes it based on the defined settings, applying the selected blocks of NER models to output the results. The toolkit generates all results with an integrated summary of the extracted entities, enabling enhanced data analysis to support the KGCP, and also, to aid further NLP tasks.