Research Papers

Context: In recent years, leveraging machine learning (ML) techniques has become one of the main solutions to tackle many software engineering (SE) tasks, in research studies (ML4SE). This has been achieved by utilizing state-of-the-art models that tend to be more complex and black-box, which is led to less explainable solutions that reduce trust and uptake of ML4SE solutions by professionals in the industry. Objective: One potential remedy is to offer explainable AI (XAI) methods to provide the missing explainability. In this paper, we aim to explore to what extent XAI has been studied in the SE community (XAI4SE) and provide a comprehensive view of the current state-of-the-art as well as challenge and roadmap for future work. Method: We conduct a systematic literature review on 24 (out of 869 primary studies that were selected by keyword search) most relevant published studies in XAI4SE. We have three research questions that were answered by meta-analysis of the collected data per paper. Results: Our study reveals that among the identified studies, software maintenance (\%68) and particularly defect prediction has the highest share on the SE stages and tasks being studied. Additionally, we found that XAI methods were mainly applied to classic ML models rather than more complex models. We also noticed a clear lack of standard evaluation metrics for XAI methods in the literature which has caused confusion among researchers and a lack of benchmarks for comparisons. Conclusions: XAI has been identified as a helpful tool by most studies, which we cover in the systematic review. However, XAI4SE is a relatively new domain with a lot of untouched potentials, including the SE tasks to help with, the ML4SE methods to explain, and the types of explanations to offer. This study encourages the researchers to work on the identified challenges and roadmap reported in the paper.

Improving Fair Training under Correlation Shifts

Yuji Roh, Kangwook Lee, Steven Euijong Whang +1

Model fairness is an essential element for Trustworthy AI. While many techniques for model fairness have been proposed, most of them assume that the training and deployment data distributions are identical, which is often not true in practice. In particular, when the bias between labels and sensitive groups changes, the fairness of the trained model is directly influenced and can worsen. We make two contributions for solving this problem. First, we analytically show that existing in-processing fair algorithms have fundamental limits in accuracy and group fairness. We introduce the notion of correlation shifts, which can explicitly capture the change of the above bias. Second, we propose a novel pre-processing step that samples the input data to reduce correlation shifts and thus enables the in-processing approaches to overcome their limitations. We formulate an optimization problem for adjusting the data ratio among labels and sensitive groups to reflect the shifted correlation. A key benefit of our approach lies in decoupling the roles of pre- and in-processing approaches: correlation adjustment via pre-processing and unfairness mitigation on the processed data via in-processing. Experiments show that our framework effectively improves existing in-processing fair algorithms w.r.t. accuracy and fairness, both on synthetic and real datasets.

Artificial Intelligence (AI) is at the forefront of modern technology, and its effects are felt in many areas of society. To prevent algorithmic disparities, fairness, accountability, transparency, and ethics (FATE) in AI are being implemented. However, the current discourse on these issues is largely dominated by more economically developed countries (MEDC), leaving out local knowledge, cultural pluralism, and global fairness. This study aims to address this gap by examining FATE-related desiderata, particularly transparency and ethics, in areas of the global South that are underserved by AI. A user study (n=43) and a participatory session (n=30) were conducted to achieve this goal. The results showed that AI models can encode bias and amplify stereotypes. To promote inclusivity, a community-led strategy is proposed to collect and curate representative data for responsible AI design. This will enable the affected community or individuals to monitor the increasing use of AI-powered systems. Additionally, recommendations based on public input are provided to ensure that AI adheres to social values and context-specific FATE needs.

From Kepler to Newton: Explainable AI for Science

Zelong Li, Jianchao Ji, Yongfeng Zhang

The Observation--Hypothesis--Prediction--Experimentation loop paradigm for scientific research has been practiced by researchers for years towards scientific discoveries. However, with data explosion in both mega-scale and milli-scale scientific research, it has been sometimes very difficult to manually analyze the data and propose new hypotheses to drive the cycle for scientific discovery. In this paper, we discuss the role of Explainable AI in scientific discovery process by demonstrating an Explainable AI-based paradigm for science discovery. The key is to use Explainable AI to help derive data or model interpretations, hypotheses, as well as scientific discoveries or insights. We show how computational and data-intensive methodology -- together with experimental and theoretical methodology -- can be seamlessly integrated for scientific research. To demonstrate the AI-based science discovery process, and to pay our respect to some of the greatest minds in human history, we show how Kepler's laws of planetary motion and Newton's law of universal gravitation can be rediscovered by (Explainable) AI based on Tycho Brahe's astronomical observation data, whose works were leading the scientific revolution in the 16-17th century. This work also highlights the important role of Explainable AI (as compared to Blackbox AI) in science discovery to help humans prevent or better prepare for the possible technological singularity that may happen in the future, since science is not only about the know how, but also the know why. Presentation of the work is available at https://slideslive.com/38986142/from-kepler-to-newton-explainable-ai-for-science-discovery.

ECQ$^{\text{x}}$: Explainability-Driven Quantization for Low-Bit and Sparse DNNs

Daniel Becking, Maximilian Dreyer, Wojciech Samek +2

The remarkable success of deep neural networks (DNNs) in various applications is accompanied by a significant increase in network parameters and arithmetic operations. Such increases in memory and computational demands make deep learning prohibitive for resource-constrained hardware platforms such as mobile devices. Recent efforts aim to reduce these overheads, while preserving model performance as much as possible, and include parameter reduction techniques, parameter quantization, and lossless compression techniques. In this chapter, we develop and describe a novel quantization paradigm for DNNs: Our method leverages concepts of explainable AI (XAI) and concepts of information theory: Instead of assigning weight values based on their distances to the quantization clusters, the assignment function additionally considers weight relevances obtained from Layer-wise Relevance Propagation (LRP) and the information content of the clusters (entropy optimization). The ultimate goal is to preserve the most relevant weights in quantization clusters of highest information content. Experimental results show that this novel Entropy-Constrained and XAI-adjusted Quantization (ECQ$^{\text{x}}$) method generates ultra low-precision (2-5 bit) and simultaneously sparse neural networks while maintaining or even improving model performance. Due to reduced parameter precision and high number of zero-elements, the rendered networks are highly compressible in terms of file size, up to $103\times$ compared to the full-precision unquantized DNN model. Our approach was evaluated on different types of models and datasets (including Google Speech Commands, CIFAR-10 and Pascal VOC) and compared with previous work.

Automated Machine Learning (AutoML) is a rapidly growing set of technologies that automate the model development pipeline by searching model space and generating candidate models. A critical, final step of AutoML is human selection of a final model from dozens of candidates. In current AutoML systems, selection is supported only by performance metrics. Prior work has shown that in practice, people evaluate ML models based on additional criteria, such as the way a model makes predictions. Comparison may happen at multiple levels, from types of errors, to feature importance, to how the model makes predictions of specific instances. We developed \tool{} to support interactive model comparison for AutoML by integrating multiple Explainable AI (XAI) and visualization techniques. We conducted a user study in which we both evaluated the system and used it as a technology probe to understand how users perform model comparison in an AutoML system. We discuss design implications for utilizing XAI techniques for model comparison and supporting the unique needs of data scientists in comparing AutoML models.

Artificial Intelligence (AI) systems exert a growing influence on our society. As they become more ubiquitous, their potential negative impacts also become evident through various real-world incidents. Following such early incidents, academic and public discussion on AI ethics has highlighted the need for implementing ethics in AI system development. However, little currently exists in the way of frameworks for understanding the practical implementation of AI ethics. In this paper, we discuss a research framework for implementing AI ethics in industrial settings. The framework presents a starting point for empirical studies into AI ethics but is still being developed further based on its practical utilization.

A new wave of decision-support systems are being built today using AI services that draw insights from data (like text and video) and incorporate them in human-in-the-loop assistance. However, just as we expect humans to be ethical, the same expectation needs to be met by automated systems that increasingly get delegated to act on their behalf. A very important aspect of an ethical behavior is to avoid (intended, perceived, or accidental) bias. Bias occurs when the data distribution is not representative enough of the natural phenomenon one wants to model and reason about. The possibly biased behavior of a service is hard to detect and handle if the AI service is merely being used and not developed from scratch, since the training data set is not available. In this situation, we envisage a 3rd party rating agency that is independent of the API producer or consumer and has its own set of biased and unbiased data, with customizable distributions. We propose a 2-step rating approach that generates bias ratings signifying whether the AI service is unbiased compensating, data-sensitive biased, or biased. The approach also works on composite services. We implement it in the context of text translation and report interesting results.

This late-breaking work presents a large-scale analysis of explainable AI (XAI) literature to evaluate claims of human explainability. We collaborated with a professional librarian to identify 18,254 papers containing keywords related to explainability and interpretability. Of these, we find that only 253 papers included terms suggesting human involvement in evaluating an XAI technique, and just 128 of those conducted some form of a human study. In other words, fewer than 1% of XAI papers (0.7%) provide empirical evidence of human explainability when compared to the broader body of XAI literature. Our findings underscore a critical gap between claims of human explainability and evidence-based validation, raising concerns about the rigor of XAI research. We call for increased emphasis on human evaluations in XAI studies and provide our literature search methodology to enable both reproducibility and further investigation into this widespread issue.

Explainable AI (XAI) is concerned with how to make AI models more understandable to people. To date these explanations have predominantly been technocentric - mechanistic or productivity oriented. This paper introduces the Explainable AI for the Arts (XAIxArts) manifesto to provoke new ways of thinking about explainability and AI beyond technocentric discourses. Manifestos offer a means to communicate ideas, amplify unheard voices, and foster reflection on practice. To supports the co-creation and revision of the XAIxArts manifesto we combine a World Café style discussion format with a living manifesto to question four core themes: 1) Empowerment, Inclusion, and Fairness; 2) Valuing Artistic Practice; 3) Hacking and Glitches; and 4) Openness. Through our interactive living manifesto experience we invite participants to actively engage in shaping this XIAxArts vision within the CHI community and beyond.

Youth are active users and stakeholders of artificial intelligence (AI), yet they are often not included in responsible AI (RAI) practices. Emerging efforts in RAI largely focus on adult populations, missing an opportunity to get unique perspectives of youth. This study explores the potential of youth (teens under the age of 18) to engage meaningfully in RAI, specifically through AI auditing. In a workshop study with 17 teens, we investigated how youth can actively identify problematic behaviors in youth-relevant ubiquitous AI (text-to-image generative AI, autocompletion in search bar, image search) and the impacts of supporting AI auditing with critical AI literacy scaffolding with guided discussion about AI ethics and an auditing tool. We found that youth can contribute quality insights, shaped by their expertise (e.g., hobbies and passions), lived experiences (e.g., social identities), and age-related knowledge (e.g., understanding of fast-moving trends). We discuss how empowering youth in AI auditing can result in more responsible AI, support their learning through doing, and lead to implications for including youth in various participatory RAI processes.

Evaluating the Effectiveness of XAI Techniques for Encoder-Based Language Models

Melkamu Abay Mersha, Mesay Gemeda Yigezu, Jugal Kalita

The black-box nature of large language models (LLMs) necessitates the development of eXplainable AI (XAI) techniques for transparency and trustworthiness. However, evaluating these techniques remains a challenge. This study presents a general evaluation framework using four key metrics: Human-reasoning Agreement (HA), Robustness, Consistency, and Contrastivity. We assess the effectiveness of six explainability techniques from five different XAI categories model simplification (LIME), perturbation-based methods (SHAP), gradient-based approaches (InputXGradient, Grad-CAM), Layer-wise Relevance Propagation (LRP), and attention mechanisms-based explainability methods (Attention Mechanism Visualization, AMV) across five encoder-based language models: TinyBERT, BERTbase, BERTlarge, XLM-R large, and DeBERTa-xlarge, using the IMDB Movie Reviews and Tweet Sentiment Extraction (TSE) datasets. Our findings show that the model simplification-based XAI method (LIME) consistently outperforms across multiple metrics and models, significantly excelling in HA with a score of 0.9685 on DeBERTa-xlarge, robustness, and consistency as the complexity of large language models increases. AMV demonstrates the best Robustness, with scores as low as 0.0020. It also excels in Consistency, achieving near-perfect scores of 0.9999 across all models. Regarding Contrastivity, LRP performs the best, particularly on more complex models, with scores up to 0.9371.