From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap

The rapid expansion of foundation models (FMs), such as large language models (LLMs), has given rise to FMware--software systems that integrate FMs as core components. While building demonstration-level FMware is relatively straightforward, transitioning to production-ready systems presents numerous challenges, including reliability, high implementation costs, scalability, and compliance with privacy regulations. This paper provides a thematic analysis of the key obstacles in productionizing FMware, synthesized from industry experience and diverse data sources, including hands-on involvement in the Open Platform for Enterprise AI (OPEA) and FMware lifecycle engineering. We identify critical issues in FM selection, data and model alignment, prompt engineering, agent orchestration, system testing, and deployment, alongside cross-cutting concerns such as memory management, observability, and feedback integration. We discuss needed technologies and strategies to address these challenges and offer guidance on how to enable the transition from demonstration systems to scalable, production-ready FMware solutions. Our findings underscore the importance of continued research and multi-industry collaboration to advance the development of production-ready FMware.

PromptExp: Multi-granularity Prompt Explanation of Large Language Models

Large Language Models excel in tasks like natural language understanding and text generation. Prompt engineering plays a critical role in leveraging LLM effectively. However, LLMs black-box nature hinders its interpretability and effective prompting engineering. A wide range of model explanation approaches have been developed for deep learning models, However, these local explanations are designed for single-output tasks like classification and regression,and cannot be directly applied to LLMs, which generate sequences of tokens. Recent efforts in LLM explanation focus on natural language explanations, but they are prone to hallucinations and inaccuracies. To address this, we introduce OurTool, a framework for multi-granularity prompt explanations by aggregating token-level insights. OurTool introduces two token-level explanation approaches: 1.an aggregation-based approach combining local explanation techniques, and 2. a perturbation-based approach with novel techniques to evaluate token masking impact. OurTool supports both white-box and black-box explanations and extends explanations to higher granularity levels, enabling flexible analysis. We evaluate OurTool in case studies such as sentiment analysis, showing the perturbation-based approach performs best using semantic similarity to assess perturbation impact. Furthermore, we conducted a user study to confirm OurTool's accuracy and practical value, and demonstrate its potential to enhance LLM interpretability.

Data Quality Antipatterns for Software Analytics

Background: Data quality is vital in software analytics, particularly for machine learning (ML) applications like software defect prediction (SDP). Despite the widespread use of ML in software engineering, the effect of data quality antipatterns on these models remains underexplored. Objective: This study develops a taxonomy of ML-specific data quality antipatterns and assesses their impact on software analytics models' performance and interpretation. Methods: We identified eight types and 14 sub-types of ML-specific data quality antipatterns through a literature review. We conducted experiments to determine the prevalence of these antipatterns in SDP data (RQ1), assess how cleaning order affects model performance (RQ2), evaluate the impact of antipattern removal on performance (RQ3), and examine the consistency of interpretation from models built with different antipatterns (RQ4). Results: In our SDP case study, we identified nine antipatterns. Over 90% of these overlapped at both row and column levels, complicating cleaning prioritization and risking excessive data removal. The order of cleaning significantly impacts ML model performance, with neural networks being more resilient to cleaning order changes than simpler models like logistic regression. Antipatterns such as Tailed Distributions and Class Overlap show a statistically significant correlation with performance metrics when other antipatterns are cleaned. Models built with different antipatterns showed moderate consistency in interpretation results. Conclusion: The cleaning order of different antipatterns impacts ML model performance. Five antipatterns have a statistically significant correlation with model performance when others are cleaned. Additionally, model interpretation is moderately affected by different data quality antipatterns.

Studying the Impact of TensorFlow and PyTorch Bindings on Machine Learning Software Quality

Bindings for machine learning frameworks (such as TensorFlow and PyTorch) allow developers to integrate a framework's functionality using a programming language different from the framework's default language (usually Python). In this paper, we study the impact of using TensorFlow and PyTorch bindings in C#, Rust, Python and JavaScript on the software quality in terms of correctness (training and test accuracy) and time cost (training and inference time) when training and performing inference on five widely used deep learning models. Our experiments show that a model can be trained in one binding and used for inference in another binding for the same framework without losing accuracy. Our study is the first to show that using a non-default binding can help improve machine learning software quality from the time cost perspective compared to the default Python binding while still achieving the same level of correctness.

Rethinking Software Engineering in the Foundation Model Era: A Curated Catalogue of Challenges in the Development of Trustworthy FMware

Foundation models (FMs), such as Large Language Models (LLMs), have revolutionized software development by enabling new use cases and business models. We refer to software built using FMs as FMware. The unique properties of FMware (e.g., prompts, agents, and the need for orchestration), coupled with the intrinsic limitations of FMs (e.g., hallucination) lead to a completely new set of software engineering challenges. Based on our industrial experience, we identified 10 key SE4FMware challenges that have caused enterprise FMware development to be unproductive, costly, and risky. In this paper, we discuss these challenges in detail and state the path for innovation that we envision. Next, we present FMArts, which is our long-term effort towards creating a cradle-to-grave platform for the engineering of trustworthy FMware. Finally, we (i) show how the unique properties of FMArts enabled us to design and develop a complex FMware for a large customer in a timely manner and (ii) discuss the lessons that we learned in doing so. We hope that the disclosure of the aforementioned challenges and our associated efforts to tackle them will not only raise awareness but also promote deeper and further discussions, knowledge sharing, and innovative solutions across the software engineering discipline.

Keeping Deep Learning Models in Check: A History-Based Approach to Mitigate Overfitting

In software engineering, deep learning models are increasingly deployed for critical tasks such as bug detection and code review. However, overfitting remains a challenge that affects the quality, reliability, and trustworthiness of software systems that utilize deep learning models. Overfitting can be (1) prevented (e.g., using dropout or early stopping) or (2) detected in a trained model (e.g., using correlation-based approaches). Both overfitting detection and prevention approaches that are currently used have constraints (e.g., requiring modification of the model structure, and high computing resources). In this paper, we propose a simple, yet powerful approach that can both detect and prevent overfitting based on the training history (i.e., validation losses). Our approach first trains a time series classifier on training histories of overfit models. This classifier is then used to detect if a trained model is overfit. In addition, our trained classifier can be used to prevent overfitting by identifying the optimal point to stop a model's training. We evaluate our approach on its ability to identify and prevent overfitting in real-world samples. We compare our approach against correlation-based detection approaches and the most commonly used prevention approach (i.e., early stopping). Our approach achieves an F1 score of 0.91 which is at least 5% higher than the current best-performing non-intrusive overfitting detection approach. Furthermore, our approach can stop training to avoid overfitting at least 32% of the times earlier than early stopping and has the same or a better rate of returning the best model.

The Impact of Using Regression Models to Build Defect Classifiers

It is common practice to discretize continuous defect counts into defective and non-defective classes and use them as a target variable when building defect classifiers (discretized classifiers). However, this discretization of continuous defect counts leads to information loss that might affect the performance and interpretation of defect classifiers. Another possible approach to build defect classifiers is through the use of regression models then discretizing the predicted defect counts into defective and non-defective classes (regression-based classifiers). In this paper, we compare the performance and interpretation of defect classifiers that are built using both approaches (i.e., discretized classifiers and regression-based classifiers) across six commonly used machine learning classifiers (i.e., linear/logistic regression, random forest, KNN, SVM, CART, and neural networks) and 17 datasets. We find that: i) Random forest based classifiers outperform other classifiers (best AUC) for both classifier building approaches; ii) In contrast to common practice, building a defect classifier using discretized defect counts (i.e., discretized classifiers) does not always lead to better performance. Hence we suggest that future defect classification studies should consider building regression-based classifiers (in particular when the defective ratio of the modeled dataset is low). Moreover, we suggest that both approaches for building defect classifiers should be explored, so the best-performing classifier can be used when determining the most influential features.

Impact of Discretization Noise of the Dependent variable on Machine Learning Classifiers in Software Engineering

Researchers usually discretize a continuous dependent variable into two target classes by introducing an artificial discretization threshold (e.g., median). However, such discretization may introduce noise (i.e., discretization noise) due to ambiguous class loyalty of data points that are close to the artificial threshold. Previous studies do not provide a clear directive on the impact of discretization noise on the classifiers and how to handle such noise. In this paper, we propose a framework to help researchers and practitioners systematically estimate the impact of discretization noise on classifiers in terms of its impact on various performance measures and the interpretation of classifiers. Through a case study of 7 software engineering datasets, we find that: 1) discretization noise affects the different performance measures of a classifier differently for different datasets; 2) Though the interpretation of the classifiers are impacted by the discretization noise on the whole, the top 3 most important features are not affected by the discretization noise. Therefore, we suggest that practitioners and researchers use our framework to understand the impact of discretization noise on the performance of their built classifiers and estimate the exact amount of discretization noise to be discarded from the dataset to avoid the negative impact of such noise.

The impact of feature importance methods on the interpretation of defect classifiers

Classifier specific (CS) and classifier agnostic (CA) feature importance methods are widely used (often interchangeably) by prior studies to derive feature importance ranks from a defect classifier. However, different feature importance methods are likely to compute different feature importance ranks even for the same dataset and classifier. Hence such interchangeable use of feature importance methods can lead to conclusion instabilities unless there is a strong agreement among different methods. Therefore, in this paper, we evaluate the agreement between the feature importance ranks associated with the studied classifiers through a case study of 18 software projects and six commonly used classifiers. We find that: 1) The computed feature importance ranks by CA and CS methods do not always strongly agree with each other. 2) The computed feature importance ranks by the studied CA methods exhibit a strong agreement including the features reported at top-1 and top-3 ranks for a given dataset and classifier, while even the commonly used CS methods yield vastly different feature importance ranks. Such findings raise concerns about the stability of conclusions across replicated studies. We further observe that the commonly used defect datasets are rife with feature interactions and these feature interactions impact the computed feature importance ranks of the CS methods (not the CA methods). We demonstrate that removing these feature interactions, even with simple methods like CFS improves agreement between the computed feature importance ranks of CA and CS methods. In light of our findings, we provide guidelines for stakeholders and practitioners when performing model interpretation and directions for future research, e.g., future research is needed to investigate the impact of advanced feature interaction removal methods on computed feature importance ranks of different CS methods.

Towards a consistent interpretation of AIOps models

Artificial Intelligence for IT Operations (AIOps) has been adopted in organizations in various tasks, including interpreting models to identify indicators of service failures. To avoid misleading practitioners, AIOps model interpretations should be consistent (i.e., different AIOps models on the same task agree with one another on feature importance). However, many AIOps studies violate established practices in the machine learning community when deriving interpretations, such as interpreting models with suboptimal performance, though the impact of such violations on the interpretation consistency has not been studied. In this paper, we investigate the consistency of AIOps model interpretation along three dimensions: internal consistency, external consistency, and time consistency. We conduct a case study on two AIOps tasks: predicting Google cluster job failures, and Backblaze hard drive failures. We find that the randomness from learners, hyperparameter tuning, and data sampling should be controlled to generate consistent interpretations. AIOps models with AUCs greater than 0.75 yield more consistent interpretation compared to low-performing models. Finally, AIOps models that are constructed with the Sliding Window or Full History approaches have the most consistent interpretation with the trends presented in the entire datasets. Our study provides valuable guidelines for practitioners to derive consistent AIOps model interpretation.