In Large Language Models (LLMs), "reducing the domain space" for text generation refers to limiting the range of content to be utilized for generating responses. This work explores Sequential Language Model ...
详细信息
ISBN:
(纸本)9798350349603;9798350349597
In Large Language Models (LLMs), "reducing the domain space" for text generation refers to limiting the range of content to be utilized for generating responses. This work explores Sequential Language Model Integration (SLMI), which mirrors the organization and distribution of knowledge across different fields of expertise. SLMI is the technique of linking multiple LLMs in a systematic manner and creating LLM-chains. In this paper, we refer to a process of choosing, linking and connecting LLMs with other services (invoke external machine learning processes or rule based applications) as "Large Language Models as a Service" to describe a complete system with specific agency. We outline the development and evaluation process of an SLMI methodology to refine response accuracy and we evaluate the methodology in the domain of dermatology using medical knowledge paths, where gains were found regarding diagnostic accuracy.
By dividing the evolutionary stages of a research field, a researcher can identify the knowledge structure, research focus and characteristics of this field. This paper develops a visualization method to identify rese...
详细信息
The integration of blockchain technology with Ciphertext-Policy Attribute-based Encryption (CP-ABE) has addressed key challenges in distributed systems, such as mutual trust and collusion, while enhancing auditability...
详细信息
Producing accurate software models is crucial in model-driven softwareengineering (MDE). However, modeling complex systems is an error-prone task that requires deep application domain knowledge. In the past decade, s...
详细信息
ISBN:
(数字)9798400712487
ISBN:
(纸本)9798400712487
Producing accurate software models is crucial in model-driven softwareengineering (MDE). However, modeling complex systems is an error-prone task that requires deep application domain knowledge. In the past decade, several automated techniques have been proposed to support academic and industrial practitioners by providing relevant modeling operations. Nevertheless, those techniques require a huge amount of training data that cannot be available due to several factors, e.g., privacy issues. The advent of large language models (LLMs) can support the generation of synthetic data although state-of-the-art approaches are not yet supporting the generation of modeling operations. To fill the gap, we propose a conceptual framework that combines modeling event logs, intelligent modeling assistants, and the generation of modeling operations using LLMs. In particular, the architecture comprises modeling components that help the designer specify the system, record its operation within a graphical modeling environment, and automatically recommend relevant operations. In addition, we generate a completely new dataset of modeling events by telling on the most prominent LLMs currently available. As a proof of concept, we instantiate the proposed framework using a set of existing modeling tools employed in industrial use cases within different European projects. To assess the proposed methodology, we first evaluate the capability of the examined LLMs to generate realistic modeling operations by relying on well-founded distance metrics. Then, we evaluate the recommended operations by considering real-world industrial modeling artifacts. Our findings demonstrate that LLMs can generate modeling events even though the overall accuracy is higher when considering human-based operations. In this respect, we see generative AI tools as an alternative when the modeling operations are not available to train traditional IMAs specifically conceived to support industrial practitioners.
Examination and evaluation are effective methods for assessing the effectiveness of teaching and the quality of talent cultivation, which are essential components of the teaching process. Traditional course assessment...
详细信息
Logs generated by large-scale software systems provide crucial information for engineers to understand the system status and diagnose problems of the systems. Log parsing, which converts raw log messages into structur...
详细信息
ISBN:
(纸本)9781665457019
Logs generated by large-scale software systems provide crucial information for engineers to understand the system status and diagnose problems of the systems. Log parsing, which converts raw log messages into structured data, is the first step to enabling automated log analytics. Existing log parsers extract the common part as log templates using statistical features. However, these log parsers often fail to identify the correct templates and parameters because: 1) they often overlook the semantic meaning of log messages, and 2) they require domain-specific knowledge for different log datasets. To address the limitations of existing methods, in this paper, we propose LogPPT to capture the patterns of templates using prompt-based few-shot learning. LogPPT utilises a novel prompt tuning method to recognise keywords and parameters based on a few labelled log data. In addition, an adaptive random sampling algorithm is designed to select a small yet diverse training set. We have conducted extensive experiments on 16 public log datasets. The experimental results show that LogPPT is effective and efficient for log parsing.
Requirements analysis is crucial in software system development. With the growth of Artificial Intelligence (AI)-based solutions, this analysis has gained greater importance to create more robust and accessibility-foc...
详细信息
This research paper describes and extends the outcomes from an in- depth study investigating the difference in the expected skills requirements from junior software engineers to senior software engineers, and reflecti...
详细信息
ISBN:
(纸本)9798350351507
This research paper describes and extends the outcomes from an in- depth study investigating the difference in the expected skills requirements from junior software engineers to senior software engineers, and reflections on the findings from that study. It is a given that senior software engineers have more experience and skills than junior software engineers. However, a focus on their differing competencies and dispositions provides an enhanced mechanism for comparison. Gaps were identified in assessing 'professional knowledge' as categorized by the IEEE/ACM Computing Curriculum Overview Report (CC2020), and in assessing 'dispositions'. It appeared that the specific scenario of comparing the expected competencies between junior and senior software engineers, tested the framework for assessing competencies developed in the CC2020 project and applied in its mapping to the IEEE/ACM Computer Science (CS2013) approved curriculum. In this study into the difference between Junior and Senior software Engineers, an initial review of relevant literature was conducted. The review found that research analyzing job requirements for software engineers of different levels was limited;'experience' as a keyword was seldom mentioned;and a common distinction was made between 'soft' and 'hard' skills - the latter being skills that were 'technical', such as programming languages, frameworks, libraries, and tools, whereas soft skills referred to skills such as personality traits, attitudes, and teamwork skills. In our extension of that work the notion of soft skills was unpacked into professional skills and dispositions. The process of mapping from the CC2020 competency framework to the CS2013 curriculum had deliberately modelled how to represent a competency-based rather than a knowledge-based curriculum. The critical deficiency identified here was the limitation imposed by adopting a skills framework based on the cognitive taxonomy, and thereby unwittingly omitting the crucial compani
This paper proposes a marker-based Augmented Reality (AR) electric circuit meant to help students grasp the knowledge of electrical circuits, especially the usage of capacitors. Recognizing components like the battery...
详细信息
Graph neural network is an effective deep learning framework for learning graph data. Existing research has introduced different variants of graph neural networks into the field of software defects and has achieved pr...
详细信息
暂无评论