This study presents a novel approach to enhance Large Language Models (LLMs) like Alpaca by dynamically integrating real-time information. This method addresses the issue of content hallucination and data relevancy by automatically collecting and integrating current data from credible sources into model prompts. Experiments show a significant improvement in accuracy and a decrease in content hallucination, with a manageable increase in response time. The research underscores the potential of real-time data integration in making LLMs more accurate and contextually relevant, setting a foundation for future advancements in dynamic data processing in AI.

Fake news detection has become a significant topic based on the fast-spreading and detrimental effects of such news. Many methods based on deep neural networks learn clues from claim content and message propagation structure or temporal information, which have been widely recognized. However, such models (i) ignore the fact that information quality is uneven in propagation, which makes semantic representations unreliable. (ii) Most models do not fully leverage spatial and temporal structure in combination. (iii) Finally, internal decision-making processes and results are non-transparent and unexplained. In this study, we develop a trust-aware evidence reasoning and spatiotemporal feature aggregation model for more interpretable and accurate fake news detection. Specifically, we first design a trust-aware evidence reasoning module to calculate the credibility of posts based on a random walk model to discover high-quality evidence. Next, from the perspective of spatiotemporal structure, we design an evidence-representation module to capture the semantic interactions granularly and enhance the reliable representation of evidence. Finally, a two-layer capsule network is designed to aggregate the implicit bias in evidence while capturing the false portions of source information in a transparent and interpretable manner. Extensive experiments on two benchmark datasets indicate that the proposed model can provide explanations for fake news detection results, as well as can achieve better performance, boosting 3.5% in F1-score on average.

Colon cancer is a common malignancy of digestive tract and has high incidence and mortality worldwide. As a normal flora in the human gastrointestinal tract, lactic acid bacteria have been proved to have health benefits, such as immune-regulation, anti-infection, and anti-tumor. In the present study, the inhibitory effects of 19 heat-inactivated plant-derived lactic acid bacteria on human colon cancer cell HCT116 were investigated. The results showed that heat-inactivated plant-derived lactic acid bacteria strain 729 had the strongest inhibitory effect on HCT116 cells among all tested bacteria. Treatment with heat-inactivated bacteria strain 729 could inhibit the proliferation of HCT-116 cells in dose-dependent manner, with 54.52% inhibition at a final concentration of 1×10⁸ CFU/mL. Moreover, the heat-inactivated bacteria strain 729 could block the cell cycle, induce apoptosis, and promote cellular ferroptosis by downregulating the expression of GPX4 and xCT at protein level. According to the 16S rDNA sequencing, the plant-derived lactic acid bacteria strain 729 was Lactobacillus plantarum. Collectively, the results indicates that lactic acid bacteria strain 729 may be developed as special ingredients targeting colon cancer, but further in vivo studies are required.