Large pre-trained language models have become popular for many applications and form an important backbone of many downstream tasks in natural language processing (NLP). Applying 'explainable artificial intelligence' (XAI) techniques to enrich such models' outputs is considered crucial for assuring their quality and shedding light on their inner workings. However, large language models are trained on a plethora of data containing a variety of biases, such as gender biases, affecting model weights and, potentially, behavior. Currently, it is unclear to what extent such biases also impact model explanations in possibly unfavorable ways. We create a gender-controlled text dataset, GECO, in which otherwise identical sentences appear in male and female forms. This gives rise to ground-truth 'world explanations' for gender classification tasks, enabling the objective evaluation of the correctness of XAI methods. We also provide GECOBench, a rigorous quantitative evaluation framework benchmarking popular XAI methods, applying them to pre-trained language models fine-tuned to different degrees. This allows us to investigate how pre-training induces undesirable bias in model explanations and to what extent fine-tuning can mitigate such explanation bias. We show a clear dependency between explanation performance and the number of fine-tuned layers, where XAI methods are observed to particularly benefit from fine-tuning or complete retraining of embedding layers. Remarkably, this relationship holds for models achieving similar classification performance on the same task. With that, we highlight the utility of the proposed gender-controlled dataset and novel benchmarking approach for research and development of novel XAI methods. All code including dataset generation, model training, evaluation and visualization is available at: https://github.com/braindatalab/gecobench
Explainable Artificial Intelligence (XAI) methods help to understand the internal mechanism of machine learning models and how they reach a specific decision or made a specific action. The list of informative features is one of the most common output of XAI methods. Multicollinearity is one of the big issue that should be considered when XAI generates the explanation in terms of the most informative features in an AI system. No review has been dedicated to investigate the current approaches to handle such significant issue. In this paper, we provide a review of the current state-of-the-art approaches in relation to the XAI in the context of recent advances in dealing with the multicollinearity issue. To do so, we searched in three repositories that are: Web of Science, Scopus and IEEE Xplore to find pertinent published papers. After excluding irrelevant papers, seven papers were considered in the review. In addition, we discuss the current XAI methods and their limitations in dealing with the multicollinearity and suggest future directions.
Explainable Artificial Intelligence (XAI) has become a widely discussed topic, the related technologies facilitate better understanding of conventional black-box models like Random Forest, Neural Networks and etc. However, domain-specific applications of XAI are still insufficient. To fill this gap, this research analyzes various machine learning models to the tasks of binary and multi-class classification for intrusion detection from network traffic on the same dataset using occlusion sensitivity. The models evaluated include Linear Regression, Logistic Regression, Linear Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Random Forest, Decision Trees, and Multi-Layer Perceptrons (MLP). We trained all models to the accuracy of 90\% on the UNSW-NB15 Dataset. We found that most classifiers leverage only less than three critical features to achieve such accuracies, indicating that effective feature engineering could actually be far more important for intrusion detection than applying complicated models. We also discover that Random Forest provides the best performance in terms of accuracy, time efficiency and robustness. Data and code available at https://github.com/pcwhy/XML-IntrusionDetection.git
Conversational explainable artificial intelligence (ConvXAI) systems based on large language models (LLMs) have garnered significant interest from the research community in natural language processing (NLP) and human-computer interaction (HCI). Such systems can provide answers to user questions about explanations in dialogues, have the potential to enhance users' comprehension and offer more information about the decision-making and generation processes of LLMs. Currently available ConvXAI systems are based on intent recognition rather than free chat, as this has been found to be more precise and reliable in identifying users' intentions. However, the recognition of intents still presents a challenge in the case of ConvXAI, since little training data exist and the domain is highly specific, as there is a broad range of XAI methods to map requests onto. In order to bridge this gap, we present CoXQL, the first dataset in the NLP domain for user intent recognition in ConvXAI, covering 31 intents, seven of which require filling multiple slots. Subsequently, we enhance an existing parsing approach by incorporating template validations, and conduct an evaluation of several LLMs on CoXQL using different parsing strategies. We conclude that the improved parsing approach (MP+) surpasses the performance of previous approaches. We also discover that intents with multiple slots remain highly challenging for LLMs.
A high-velocity paradigm shift towards Explainable Artificial Intelligence (XAI) has emerged in recent years. Highly complex Machine Learning (ML) models have flourished in many tasks of intelligence, and the questions have started to shift away from traditional metrics of validity towards something deeper: What is this model telling me about my data, and how is it arriving at these conclusions? Inconsistencies between XAI and modeling techniques can have the undesirable effect of casting doubt upon the efficacy of these explainability approaches. To address these problems, we propose a systematic, perturbation-based analysis against a popular, model-agnostic method in XAI, SHapley Additive exPlanations (Shap). We devise algorithms to generate relative feature importance in settings of dynamic inference amongst a suite of popular machine learning and deep learning methods, and metrics that allow us to quantify how well explanations generated under the static case hold. We propose a taxonomy for feature importance methodology, measure alignment, and observe quantifiable similarity amongst explanation models across several datasets.
Counterfactual (CF) explanations for ML model predictions provide actionable recourse recommendations to individuals adversely impacted by predicted outcomes. However, despite being preferred by end-users, CF explanations have been shown to pose significant security risks in real-world applications; in particular, malicious adversaries can exploit CF explanations to perform query-efficient model extraction attacks on the underlying proprietary ML model. To address this security challenge, we propose CFMark, a novel model-agnostic watermarking framework for detecting unauthorized model extraction attacks relying on CF explanations. CFMark involves a novel bi-level optimization problem to embed an indistinguishable watermark into the generated CF explanation such that any future model extraction attacks using these watermarked CF explanations can be detected using a null hypothesis significance testing (NHST) scheme. At the same time, the embedded watermark does not compromise the quality of the CF explanations. We evaluate CFMark across diverse real-world datasets, CF explanation methods, and model extraction techniques. Our empirical results demonstrate CFMark's effectiveness, achieving an F-1 score of ~0.89 in identifying unauthorized model extraction attacks using watermarked CF explanations. Importantly, this watermarking incurs only a negligible degradation in the quality of generated CF explanations (i.e., ~1.3% degradation in validity and ~1.6% in proximity). Our work establishes a critical foundation for the secure deployment of CF explanations in real-world applications.
We introduce Discovering Conceptual Network Explanations (DCNE), a new approach for generating human-comprehensible visual explanations to enhance the interpretability of deep neural image classifiers. Our method automatically finds visual explanations that are critical for discriminating between classes. This is achieved by simultaneously optimizing three criteria: the explanations should be few, diverse, and human-interpretable. Our approach builds on the recently introduced Concept Relevance Propagation (CRP) explainability method. While CRP is effective at describing individual neuronal activations, it generates too many concepts, which impacts human comprehension. Instead, DCNE selects the few most important explanations. We introduce a new evaluation dataset centered on the challenging task of classifying birds, enabling us to compare the alignment of DCNE's explanations to those of human expert-defined ones. Compared to existing eXplainable Artificial Intelligence (XAI) methods, DCNE has a desirable trade-off between conciseness and completeness when summarizing network explanations. It produces 1/30 of CRP's explanations while only resulting in a slight reduction in explanation quality. DCNE represents a step forward in making neural network decisions accessible and interpretable to humans, providing a valuable tool for both researchers and practitioners in XAI and model alignment.
In this paper, we demonstrate the feasibility of alterfactual explanations for black box image classifiers. Traditional explanation mechanisms from the field of Counterfactual Thinking are a widely-used paradigm for Explainable Artificial Intelligence (XAI), as they follow a natural way of reasoning that humans are familiar with. However, most common approaches from this field are based on communicating information about features or characteristics that are especially important for an AI's decision. However, to fully understand a decision, not only knowledge about relevant features is needed, but the awareness of irrelevant information also highly contributes to the creation of a user's mental model of an AI system. To this end, a novel approach for explaining AI systems called alterfactual explanations was recently proposed on a conceptual level. It is based on showing an alternative reality where irrelevant features of an AI's input are altered. By doing so, the user directly sees which input data characteristics can change arbitrarily without influencing the AI's decision. In this paper, we show for the first time that it is possible to apply this idea to black box models based on neural networks. To this end, we present a GAN-based approach to generate these alterfactual explanations for binary image classifiers. Further, we present a user study that gives interesting insights on how alterfactual explanations can complement counterfactual explanations.
Ownership verification is currently the most critical and widely adopted post-hoc method to safeguard model copyright. In general, model owners exploit it to identify whether a given suspicious third-party model is stolen from them by examining whether it has particular properties `inherited' from their released models. Currently, backdoor-based model watermarks are the primary and cutting-edge methods to implant such properties in the released models. However, backdoor-based methods have two fatal drawbacks, including harmfulness and ambiguity. The former indicates that they introduce maliciously controllable misclassification behaviors ($i.e.$, backdoor) to the watermarked released models. The latter denotes that malicious users can easily pass the verification by finding other misclassified samples, leading to ownership ambiguity. In this paper, we argue that both limitations stem from the `zero-bit' nature of existing watermarking schemes, where they exploit the status ($i.e.$, misclassified) of predictions for verification. Motivated by this understanding, we design a new watermarking paradigm, $i.e.$, Explanation as a Watermark (EaaW), that implants verification behaviors into the explanation of feature attribution instead of model predictions. Specifically, EaaW embeds a `multi-bit' watermark into the feature attribution explanation of specific trigger samples without changing the original prediction. We correspondingly design the watermark embedding and extraction algorithms inspired by explainable artificial intelligence. In particular, our approach can be used for different tasks ($e.g.$, image classification and text generation). Extensive experiments verify the effectiveness and harmlessness of our EaaW and its resistance to potential attacks.
The Model Parameter Randomisation Test (MPRT) is highly recognised in the eXplainable Artificial Intelligence (XAI) community due to its fundamental evaluative criterion: explanations should be sensitive to the parameters of the model they seek to explain. However, recent studies have raised several methodological concerns for the empirical interpretation of MPRT. In response, we propose two modifications to the original test: Smooth MPRT and Efficient MPRT. The former reduces the impact of noise on evaluation outcomes via sampling, while the latter avoids the need for biased similarity measurements by re-interpreting the test through the increase in explanation complexity after full model randomisation. Our experiments show that these modifications enhance the metric reliability, facilitating a more trustworthy deployment of explanation methods.
Blocking events are an important cause of extreme weather, especially long-lasting blocking events that trap weather systems in place. The duration of blocking events is, however, underestimated in climate models. Explainable Artificial Intelligence are a class of data analysis methods that can help identify physical causes of prolonged blocking events and diagnose model deficiencies. We demonstrate this approach on an idealized quasigeostrophic model developed by Marshall and Molteni (1993). We train a convolutional neural network (CNN), and subsequently, build a sparse predictive model for the persistence of Atlantic blocking, conditioned on an initial high-pressure anomaly. Shapley Additive ExPlanation (SHAP) analysis reveals that high-pressure anomalies in the American Southeast and North Atlantic, separated by a trough over Atlantic Canada, contribute significantly to prediction of sustained blocking events in the Atlantic region. This agrees with previous work that identified precursors in the same regions via wave train analysis. When we apply the same CNN to blockings in the ERA5 atmospheric reanalysis, there is insufficient data to accurately predict persistent blocks. We partially overcome this limitation by pre-training the CNN on the plentiful data of the Marshall-Molteni model, and then using Transfer Learning to achieve better predictions than direct training. SHAP analysis before and after transfer learning allows a comparison between the predictive features in the reanalysis and the quasigeostrophic model, quantifying dynamical biases in the idealized model. This work demonstrates the potential for machine learning methods to extract meaningful precursors of extreme weather events and achieve better prediction using limited observational data.
Deep learning models are widely applied in the signal processing community, yet their inner working procedure is often treated as a black box. In this paper, we investigate the use of eXplainable Artificial Intelligence (XAI) techniques to learning-based end-to-end speech source localization models. We consider the Layer-wise Relevance Propagation (LRP) technique, which aims to determine which parts of the input are more important for the output prediction. Using LRP we analyze two state-of-the-art models, of differing architectural complexity that map audio signals acquired by the microphones to the cartesian coordinates of the source. Specifically, we inspect the relevance associated with the input features of the two models and discover that both networks denoise and de-reverberate the microphone signals to compute more accurate statistical correlations between them and consequently localize the sources. To further demonstrate this fact, we estimate the Time-Difference of Arrivals (TDoAs) via the Generalized Cross Correlation with Phase Transform (GCC-PHAT) using both microphone signals and relevance signals extracted from the two networks and show that through the latter we obtain more accurate time-delay estimation results.
Neuro-fuzzy systems are a technique of explainable artificial intelligence (XAI). They elaborate knowledge models as a set of fuzzy rules. Fuzzy sets are crucial components of fuzzy rules. They are used to model linguistic terms. In this paper, we present an automatic extraction of fuzzy rules in the natural English language. Full implementation is available free from a public repository.
As a favorable tool for explainable artificial intelligence (XAI), Shapley value has been widely used to interpret deep learning based predictive models. However, accurate and efficient estimation of Shapley value is difficult since the computation load grows exponentially with the increase of input features. Most existing accelerated estimation methods have to compromise on estimation accuracy with efficiency. In this article, we present EmSHAP(Energy-based model for Shapley value estimation) to estimate the expectation of Shapley contribution function under arbitrary subset of features given the rest. The energy-based model estimates the conditional density in the Shapley contribution function, which involves an energy network for approximating the unnormalized conditional density and a GRU (Gated Recurrent Unit) network for approximating the partition function. The GRU network maps the input features onto a hidden space to eliminate the impact of input orderings. In order to theoretically evaluate the performance of different Shapley value estimation methods, Theorems 1, 2 and 3 analyzed the error bounds of EmSHAP as well as two state-of-the-art methods, namely KernelSHAP and VAEAC. It is proved that EmSHAP has tighter error bound than KernelSHAP and VAEAC. Finally, case studies on two application examples show the enhanced estimation accuracy of EmSHAP.
Fairness in machine learning (ML) has received much attention. However, existing studies have mainly focused on the distributive fairness of ML models. The other dimension of fairness, i.e., procedural fairness, has been neglected. In this paper, we first define the procedural fairness of ML models, and then give formal definitions of individual and group procedural fairness. We propose a novel metric to evaluate the group procedural fairness of ML models, called $GPF_{FAE}$, which utilizes a widely used explainable artificial intelligence technique, namely feature attribution explanation (FAE), to capture the decision process of the ML models. We validate the effectiveness of $GPF_{FAE}$ on a synthetic dataset and eight real-world datasets. Our experiments reveal the relationship between procedural and distributive fairness of the ML model. Based on our analysis, we propose a method for identifying the features that lead to the procedural unfairness of the model and propose two methods to improve procedural fairness after identifying unfair features. Our experimental results demonstrate that we can accurately identify the features that lead to procedural unfairness in the ML model, and both of our proposed methods can significantly improve procedural fairness with a slight impact on model performance, while also improving distributive fairness.
Background: Pneumothorax is an acute thoracic disease caused by abnormal air collection between the lungs and chest wall. To address the opaqueness often associated with deep learning (DL) models, explainable artificial intelligence (XAI) methods have been introduced to outline regions related to pneumothorax diagnoses made by DL models. However, these explanations sometimes diverge from actual lesion areas, highlighting the need for further improvement. Method: We propose a template-guided approach to incorporate the clinical knowledge of pneumothorax into model explanations generated by XAI methods, thereby enhancing the quality of these explanations. Utilizing one lesion delineation created by radiologists, our approach first generates a template that represents potential areas of pneumothorax occurrence. This template is then superimposed on model explanations to filter out extraneous explanations that fall outside the template's boundaries. To validate its efficacy, we carried out a comparative analysis of three XAI methods with and without our template guidance when explaining two DL models in two real-world datasets. Results: The proposed approach consistently improved baseline XAI methods across twelve benchmark scenarios built on three XAI methods, two DL models, and two datasets. The average incremental percentages, calculated by the performance improvements over the baseline performance, were 97.8% in Intersection over Union (IoU) and 94.1% in Dice Similarity Coefficient (DSC) when comparing model explanations and ground-truth lesion areas. Conclusions: In the context of pneumothorax diagnoses, we proposed a template-guided approach for improving AI explanations. We anticipate that our template guidance will forge a fresh approach to elucidating AI models by integrating clinical domain expertise.
The large success of deep learning based methods in Visual Question Answering (VQA) has concurrently increased the demand for explainable methods. Most methods in Explainable Artificial Intelligence (XAI) focus on generating post-hoc explanations rather than taking an intrinsic approach, the latter characterizing an interpretable model. In this work, we introduce an interpretable approach for graph-based VQA and demonstrate competitive performance on the GQA dataset. This approach bridges the gap between interpretability and performance. Our model is designed to intrinsically produce a subgraph during the question-answering process as its explanation, providing insight into the decision making. To evaluate the quality of these generated subgraphs, we compare them against established post-hoc explainability methods for graph neural networks, and perform a human evaluation. Moreover, we present quantitative metrics that correlate with the evaluations of human assessors, acting as automatic metrics for the generated explanatory subgraphs. Our implementation is available at https://github.com/DigitalPhonetics/Intrinsic-Subgraph-Generation-for-VQA.
With the spread and rapid advancement of black box machine learning models, the field of interpretable machine learning (IML) or explainable artificial intelligence (XAI) has become increasingly important over the last decade. This is particularly relevant for survival analysis, where the adoption of IML techniques promotes transparency, accountability and fairness in sensitive areas, such as clinical decision making processes, the development of targeted therapies, interventions or in other medical or healthcare related contexts. More specifically, explainability can uncover a survival model's potential biases and limitations and provide more mathematically sound ways to understand how and which features are influential for prediction or constitute risk factors. However, the lack of readily available IML methods may have deterred medical practitioners and policy makers in public health from leveraging the full potential of machine learning for predicting time-to-event data. We present a comprehensive review of the limited existing amount of work on IML methods for survival analysis within the context of the general IML taxonomy. In addition, we formally detail how commonly used IML methods, such as such as individual conditional expectation (ICE), partial dependence plots (PDP), accumulated local effects (ALE), different feature importance measures or Friedman's H-interaction statistics can be adapted to survival outcomes. An application of several IML methods to real data on data on under-5 year mortality of Ghanaian children from the Demographic and Health Surveys (DHS) Program serves as a tutorial or guide for researchers, on how to utilize the techniques in practice to facilitate understanding of model decisions or predictions.
It is often argued that effective human-centered explainable artificial intelligence (XAI) should resemble human reasoning. However, empirical investigations of how concepts from cognitive science can aid the design of XAI are lacking. Based on insights from cognitive science, we propose a framework of explanatory modes to analyze how people frame explanations, whether mechanistic, teleological, or counterfactual. Using the complex safety-critical domain of autonomous driving, we conduct an experiment consisting of two studies on (i) how people explain the behavior of a vehicle in 14 unique scenarios (N1=54) and (ii) how they perceive these explanations (N2=382), curating the novel Human Explanations for Autonomous Driving Decisions (HEADD) dataset. Our main finding is that participants deem teleological explanations significantly better quality than counterfactual ones, with perceived teleology being the best predictor of perceived quality. Based on our results, we argue that explanatory modes are an important axis of analysis when designing and evaluating XAI and highlight the need for a principled and empirically grounded understanding of the cognitive mechanisms of explanation. The HEADD dataset and our code are available at: https://datashare.ed.ac.uk/handle/10283/8930.
The field of explainable artificial intelligence (XAI) attempts to develop methods that provide insight into how complicated machine learning methods make predictions. Many methods of explanation have focused on the concept of feature attribution, a decomposition of the model's prediction into individual contributions corresponding to each input feature. In this work, we explore the problem of feature attribution in the context of Gaussian process regression (GPR). We take a principled approach to defining attributions under model uncertainty, extending the existing literature. We show that although GPR is a highly flexible and non-parametric approach, we can derive interpretable, closed-form expressions for the feature attributions. When using integrated gradients as an attribution method, we show that the attributions of a GPR model also follow a Gaussian process distribution, which quantifies the uncertainty in attribution arising from uncertainty in the model. We demonstrate, both through theory and experimentation, the versatility and robustness of this approach. We also show that, when applicable, the exact expressions for GPR attributions are both more accurate and less computationally expensive than the approximations currently used in practice. The source code for this project is freely available under MIT license at https://github.com/KurtButler/2024_attributions_paper.