Search

Large Language Models (LLMs) are increasingly embedded into software products across diverse industries, enhancing user experiences, but at the same time introducing numerous challenges for developers. Unique characteristics of LLMs force developers, who are accustomed to traditional software development and evaluation, out of their comfort zones as the LLM components shatter standard assumptions about software systems. This study explores the emerging solutions that software developers are adopting to navigate the encountered challenges. Leveraging a mixed-method research, including 26 interviews and a survey with 332 responses, the study identifies 19 emerging solutions regarding quality assurance that practitioners across several product teams at Microsoft are exploring. The findings provide valuable insights that can guide the development and evaluation of LLM-based products more broadly in the face of these challenges., Comment: 10 pages, 2 tables

Machine learning (ML) components are increasingly incorporated into software products for end-users, but developers face challenges in transitioning from ML prototypes to products. Academics have limited access to the source of commercial ML products, hindering research progress to address these challenges. In this study, first and foremost, we contribute a dataset of 262 open-source ML products for end users (not just models), identified among more than half a million ML-related projects on GitHub. Then, we qualitatively and quantitatively analyze 30 open-source ML products to answer six broad research questions about development practices and system architecture. We find that the majority of the ML products in our sample represent more startup-style development than reported in past interview studies. We report 21 findings, including limited involvement of data scientists in many open-source ML products, unusually low modularity between ML and non-ML code, diverse architectural choices on incorporating models into products, and limited prevalence of industry best practices such as model testing, pipeline automation, and monitoring. Additionally, we discuss seven implications of this study on research, development, and education, including the need for tools to assist teams without data scientists, education opportunities, and open-source-specific research for privacy-preserving telemetry.

Incorporating machine learning (ML) components into software products raises new software-engineering challenges and exacerbates existing challenges. Many researchers have invested significant effort in understanding the challenges of industry practitioners working on building products with ML components, through interviews and surveys with practitioners. With the intention to aggregate and present their collective findings, we conduct a meta-summary study: We collect 50 relevant papers that together interacted with over 4758 practitioners using guidelines for systematic literature reviews. We then collected, grouped, and organized the over 500 mentions of challenges within those papers. We highlight the most commonly reported challenges and hope this meta-summary will be a useful resource for the research community to prioritize research and education in this field., Comment: 15 pages, 2 figures, 3 tables, published in CAIN 2023

The documentation practice for machine-learned (ML) models often falls short of established practices for traditional software, which impedes model accountability and inadvertently abets inappropriate or misuse of models. Recently, model cards, a proposal for model documentation, have attracted notable attention, but their impact on the actual practice is unclear. In this work, we systematically study the model documentation in the field and investigate how to encourage more responsible and accountable documentation practice. Our analysis of publicly available model cards reveals a substantial gap between the proposal and the practice. We then design a tool named DocML aiming to (1) nudge the data scientists to comply with the model cards proposal during the model development, especially the sections related to ethics, and (2) assess and manage the documentation quality. A lab study reveals the benefit of our tool towards long-term documentation quality and accountability., Comment: To be published in proceedings of CHI 2023

The introduction of machine learning (ML) components in software projects has created the need for software engineers to collaborate with data scientists and other specialists. While collaboration can always be challenging, ML introduces additional challenges with its exploratory model development process, additional skills and knowledge needed, difficulties testing ML systems, need for continuous evolution and monitoring, and non-traditional quality requirements such as fairness and explainability. Through interviews with 45 practitioners from 28 organizations, we identified key collaboration challenges that teams face when building and deploying ML systems into production. We report on common collaboration points in the development of production ML systems for requirements, data, and integration, as well as corresponding team patterns and challenges. We find that most of these challenges center around communication, documentation, engineering, and process and collect recommendations to address these challenges., Comment: 22 pages, 10 figures, 5 tables

Software visualization helps to comprehend the system by providing a vivid illustration. The developers, as well as the analysts, can have a glance over the total system to understand the basic changes over time from a high-level point of view through this technique. In recent years, many tools are proposed to visualize software based on different architectural metaphors, such as as- solar system, city or park. Some of the solutions have just worked on system visualization where a few tried to explain the changes in software throughout different versions that still need heavy manual work. Keeping such limitations in mind, this paper proposes a lightweight tool named SysMap that takes the source codes of different versions of software systems, provides 3D illustrations of those systems and a graphical statistic of its evolution. To build the graphical element to represent the system, the source code has been studied to find out different software metrics. For experimentation, several open-source java projects were chosen to find out the necessary information. Henceforth, this tool will surely increase the work efficiency of both the developer and analyst by reducing the manual effort and by providing the graphical view to comprehend the software evolution over time.

Analysis of child mortality is crucial as it pertains to the policy and programs of a country. The early assessment of patterns and trends in causes of child mortality help decision-makers assess needs, prioritize interventions, and monitor progress. Post-birth factors of the child, such as real-time clinical data, health data of the child, etc. are frequently used in child mortality studies. However, in the early assessment of child mortality, pre-birth factors would be more practical and beneficial than the post-birth factors. This study aims at incorporating pre-birth factors, such as birth history, maternal history, reproduction history, socioeconomic condition, etc. for classifying child mortality. To assess the relative importance of the features, Information Gain (IG) attribute evaluator is employed. For classifying child mortality, four machine learning algorithms are evaluated. Results show that the proposed approach achieved an AUC score of 0.947 in classifying child mortality which outperformed the clinical standards. In terms of accuracy, precision, recall, and f-1 score, the results are also notable and uniform. In developing countries like Bangladesh, the early assessment of child mortality using pre-birth factors would be effective and feasible as it avoids the uncertainty of the post-birth factors., Comment: 21 pages, 2 tables

Provenance is derivative journal information about the origin and activities of system data and processes. For a highly dynamic system like the cloud, provenance can be accurately detected and securely used in cloud digital forensic investigation activities. This paper proposes watchword oriented provenance cognition algorithm for the cloud environment. Additionally time-stamp based buffer verifying algorithm is proposed for securing the access to the detected cloud provenance. Performance analysis of the novel algorithms proposed here yields a desirable detection rate of 89.33% and miss rate of 8.66%. The securing algorithm successfully rejects 64% of malicious requests, yielding a cumulative frequency of 21.43 for MR.