FinTech software, crucial for both safety and timely market deployment, presents a compelling case for automated acceptance testing against regulatory business rules. However, the inherent challenges of comprehending unstructured natural language descriptions of these rules and crafting comprehensive test cases demand human intelligence. The emergence of Large Language Models (LLMs) holds promise for automated test case generation, leveraging their natural language processing capabilities. Yet, their dependence on human intervention for effective prompting hampers efficiency. In response, we introduce a groundbreaking, fully automated approach for generating high-coverage test cases from natural language business rules. Our methodology seamlessly integrates the versatility of LLMs with the predictability of algorithmic methods. We fine-tune pre-trained LLMs for improved information extraction accuracy and algorithmically generate comprehensive testable scenarios for the extracted business rules. Our prototype, LLM4Fin, is designed for testing real-world stock-trading software. Experimental results demonstrate LLM4Fin’s superiority over both state-of-the-art LLM, such as ChatGPT, and skilled testing engineers. We achieve remarkable performance, with up to 98.18% and an average of 20%−110% improvement on business scenario coverage, and up to 93.72% on code coverage, while reducing the time cost from 20 minutes to a mere 7 seconds. These results provide robust evidence of the framework’s practical applicability and efficiency, marking a significant advancement in FinTech software testing.

Although the resultant elimination method can get all the possible solutions for the selective harmonic elimination (SHE) problem without the selection of initial values, it still has some fatal shortcomings, such as the high computation burden and the huge memory consumption caused by the intermediate expression swell in the procedure of computing the symbolic determinant of the Sylvester matrix. On the basis of the principle of polynomial interpolation, an algorithm framework is proposed to compute the resultant polynomials, which contains the following two major steps: the evaluation of numerical interpolation points and the solution of linear equations. This approach avoids symbolic computing whose computation complexity is usually very high, furthermore, both of these two steps are suitable for parallel implementing which can speed up the computing tremendously. By using the extended n ‐dimensional Björck–Pereyra's algorithm, this algorithm framework is implemented on a parallel computing system, and it has been used to solve the SHE equations for two‐level, three‐level, and multilevel inverters. As all the possible solutions can be found by this algorithm, the optimal solutions which have the lowest total harmonic distortion can be identified. Experiment results verify the correctness and effectiveness of the proposed method.

Text-to-3D (T23D) generation has transformed digital content creation, yet remains bottlenecked by blind trial-and-error prompting processes that yield unpredictable results. While visual prompt engineering has advanced in text-to-image domains, its application to 3D generation presents unique challenges requiring multi-view consistency evaluation and spatial understanding. We present Sel3DCraft, a visual prompt engineering system for T23D that transforms unstructured exploration into a guided visual process. Our approach introduces three key innovations: a dual-branch structure combining retrieval and generation for diverse candidate exploration; a multi-view hybrid scoring approach that leverages MLLMs with innovative high-level metrics to assess 3D models with human-expert consistency; and a prompt-driven visual analytics suite that enables intuitive defect identification and refinement. Extensive testing and a user study demonstrate that Sel3DCraft surpasses other T23D systems in supporting creativity for designers.

Trigger-action programming (TAP) is a new programming paradigm enabling end-users to customize their smart devices by defining simple trigger-action rules. While it offers appealing convenience to end-users, TAP renders devices vulnerable to operation chaos and security risk resulting from potential defects in the rules. Verifying TAP rules defined by end-users is thereby necessary to detect such vulnerabilities at the early stage. However, such rules are difficult to analyze because their executions are often device-specific and environment-driven. Existing approaches require modeling them with their host devices and running environments, which is labor-consuming and hard to be automated. Moreover, the composition of devices causes state explosion, rendering the conflict analysis time-consuming. In this article, we first build a large corpus of TAP rules developed by end-users. Analyzing this corpus results in six types of conflicts and reveals that nearly 90% of end-users made conflicts in their customized rules, and on average, 3.7 rules contain a conflict, which concurs with the necessity of developing practical conflict analysis techniques. Empirical analysis motivates us to propose a lightweight SMT-based approach for conflict analysis from a programmatic perspective. Compared to the existing approaches, our approach does not require modeling devices; thus, it could be fully automatic and flexible in efficiently detecting various types of conflicts. We implement the approach in a tool TapChecker. We analyze 12 514 TAP rules collected from real-world TAP platforms (10 535) and laboratory experiments (1979). Experimental results show that our approach outperforms the state-of-the-art tool regarding the number of detected conflicts and efficiency.