Empowering Discovery,
Enhancing Knowledge

We present higher Chern-Simons-Antoniadis-Savvidy (ChSAS) forms based on crossed modules. We start from introducing a generalized multilinear symmetric invariant polynomial for the differential crossed modules and constructing a metric independent, higher gauge invariant, and closed form using the higher curvature forms. Then, we establish the higher Chern-Weil theorem and prove that the higher ChSAS forms are a special case of this theorem. Finally, we get the link of two independent higher ChSAS theories.

We consider the problem of red teaming LLMs on elementary calculations and algebraic tasks to evaluate how various prompting techniques affect the quality of outputs. We present a framework to procedurally generate numerical questions and puzzles, and compare the results with and without the application of several red teaming techniques. Our findings suggest that even though structured reasoning and providing worked-out examples slow down the deterioration of the quality of answers, the gpt-3.5-turbo and gpt-4 models are not well suited for elementary calculations and reasoning tasks, also when being red teamed.

Product bundling has evolved into a crucial marketing strategy in e-commerce. However, current studies are limited to generating (1) fixed-size or single bundles, and most importantly, (2) bundles that do not reflect consistent user intents, thus being less intelligible or useful to users. This paper explores two interrelated tasks, i.e., personalized bundle generation and the underlying intent inference based on users’ interactions in a session, leveraging the logical reasoning capability of large language models. We introduce a dynamic in-context learning paradigm, which enables ChatGPT to seek tailored and dynamic lessons from closely related sessions as demonstrations while performing tasks in the target session. Specifically, it first harnesses retrieval augmented generation to identify nearest neighbor sessions for each target session. Then, proper prompts are designed to guide ChatGPT to perform the two tasks on neighbor sessions. To enhance reliability and mitigate the hallucination issue, we develop (1) a self-correction strategy to foster mutual improvement in both tasks without supervision signals; and (2) an auto-feedback mechanism to recurrently offer dynamic supervision based on the distinct mistakes made by ChatGPT on various neighbor sessions. Thus, the target session can receive customized and dynamic lessons for improved performance by observing the demonstrations of its neighbor sessions. Finally, experimental results on three real-world datasets verify the effectiveness of our methods on both tasks. Additionally, the inferred intents can prove beneficial for other intriguing downstream tasks, such as crafting appealing …

Microplastic pollution in the soil has become a growing public concern globally. The application of livestock and poultry manure compost is considered to be an important pathway for the accumulation of microplastics in soils. However, the understanding of microplastic pollution in fecal compost is still limited. In this study, the distribution characteristics of microplastics in composts of commercial chicken, cow, goat, and pig manure in four provinces of China were investigated. Microplastics in manure composts were extracted by sieving and digestion with Fenton’s reagent, and their color, size, shape, type, and abundance were further analyzed. The results show that transparent, black, red, and blue are the dominant colors of microplastics in manure composts. The shapes of microplastics in manure composts include fibers, fragments, films and granules, with fibers being the highest. The dominant size of …