The advent of large language models has facilitated the development of natural language text generation. It also poses unprecedented challenges, with content hallucination emerging as a significant concern. Existing solutions often involve expensive and complex interventions during the training process. Moreover, some approaches emphasize problem disassembly while neglecting the crucial validation process, leading to performance degradation or limited applications. To overcome these limitations, we propose a Markov Chain-based multi-agent debate verification framework to enhance hallucination detection accuracy in concise claims. Our method integrates the fact-checking process, including claim detection, evidence retrieval, and multi-agent verification. In the verification stage, we deploy multiple agents through flexible Markov Chain-based debates to validate individual claims, ensuring meticulous verification outcomes. Experimental results across three generative tasks demonstrate that our approach achieves significant improvements over baselines.

Understanding small visual objects is crucial in fields such as video surveillance, remote sensing, and autonomous driving. In this paper, we investigate the capability of advanced large vision-language models (LVLMs) to recognize and interpret small objects in visual data. To this end, we curate a specialized dataset for evaluating fine-grained visual hallucinations, incorporating two object categories and three types of hallucinations. First, we assess 11 state-of-the-art LVLMs, yielding several key insights, as anticipated, LVLMs perform significantly worse on queries related to small objects compared to regular-sized ones, with performance on regular objects proving to be an unreliable predictor of that on small objects. This finding underscores the need for dedicated research on fine-grained visual hallucinations. Second, we evaluate three training-free methods: Scaffold, Chain of Thought (CoT), and Image Resizing, all of which result in varying degrees of improvement. Furthermore, we conduct a series of detailed ablation studies on the visual encoders of Eagle-X5, examining their performance across fine-grained visual hallucination tasks. Our findings reveal that ConvNeXt architecture is critical for object existence recognition tasks. In contrast, for mitigating other types of hallucinations, integrating information from multiple visual encoders is significantly more effective than relying on a single encoder. These results highlight several promising directions for advancing small object recognition with LVLMs.

In the Industrial Internet of Things (IIoT), massive amounts of data are generated and shared among different industrial entities, and it is crucial to realize the security and flexibility of data sharing. Autonomous path proxy re-encryption technology enables the autonomous creation of an ordered data-sharing path as specified by the data owner, supporting multi-hop re-encryption. However, the security of this technology requires further enhancement. Therefore, we propose a verifiable data-sharing scheme. To prevent data leakage due to collusion between the proxy and users, we introduce blockchain technology to supervise the decryption behavior of users in the autonomous path. Second, we verify the proxy re-encryption computation, ensuring its validity. Finally, a security analysis demonstrates that the proposed scheme meets the security requirements. Furthermore, we evaluated the performance of the proposed scheme, and the results show that our scheme has only increased less overhead, but has enhanced security.

The purpose is to optimize supply chain management (SCM) programs in global organizations and promote international economic development. This paper first discusses the development of cloud technology and the international organization supply chain under big data, artificial intelligence, the internet of things, mobile internet and cloud computing (BIIMC). Then, the application design concept of cloud technology in the global organization supply chain is discussed. Finally, based on the current international organization supply chain foundation, the management optimization program is designed using cloud technology and evaluated. The results show that the program performs prominently in the SCM of Taobao and Amazon.

This paper presents a child pornographic image detection system that identifies human skin tones in digital images, extracts features to detect explicit images and performs facial image based age classification. The novelty of the technique relies on the use of a robust and very fast skin color filter and a new set of facial features for improved identification of child faces. Tests on a dataset containing explicit images taken under different illuminations and reflecting a diversity of human skin tones, show that explicit images can be differentiated from benign images with around 90% accuracy. Similarly, tests performed on adult and child facial images yielded an accuracy of 80% in detecting child faces. Test conducted on 105 images involving semi-naked children (with no sexual context) revealed that the system has true positive rates of 83% in detecting explicit-like images and 96.5% in detecting child faces.

The identification of image acquisition source is an important problem in digital image forensics. In this work, we focus on building a classifier to effectively distinguish between digital images taken from digital single lens reflex (DSLR) and compact cameras. Based on the architecture and the imaging features of DSLR and compact cameras, the images taken from different sources may have different statistical properties in both spatial and transform domains. In this work, we utilized wavelet coefficients and pixel noise statistics to model these two different source classes over 20 different digital cameras. The efficacy of the digital source class identifier, introduced in the paper, has been tested over 1000 high quality camera outputs and post-processed images (resized, re-compressed). Experimental analysis shows that the proposed method has good potential to distinguish DSLR and compact source classes.