The two-stage fine-tuning (FT) method, linear probing (LP) then fine-tuning (LP-FT), outperforms linear probing and FT alone. This holds true for both in-distribution (ID) and out-of-distribution (OOD) data.

As Artificial Intelligence (AI) is increasingly used in areas that significantly impact human lives, concerns about fairness and transparency have grown, especially regarding their impact on protected groups. Recently, the intersection of explainability and fairness has emerged as an important area to promote responsible AI systems. This paper explores how explainability methods can be leveraged to detect and interpret unfairness. We propose a pipeline that integrates local post-hoc explanation methods to derive fairness-related insights. During the pipeline design, we identify and address critical questions arising from the use of explanations as bias detectors such as the relationship between distributive and procedural fairness, the effect of removing the protected attribute, the consistency and quality of results across different explanation methods, the impact of various aggregation strategies of local explanations on group fairness evaluations, and the overall trustworthiness of explanations as bias detectors. Our results show the potential of explanation methods used for fairness while highlighting the need to carefully consider the aforementioned critical aspects.

Machine learning algorithms are increasingly being applied to fault detection and diagnosis (FDD) in chemical processes. However, existing data-driven FDD platforms often lack interpretability for process operators and struggle to identify root causes of previously unseen faults. This paper presents FaultExplainer, an interactive tool designed to improve fault detection, diagnosis, and explanation in the Tennessee Eastman Process (TEP). FaultExplainer integrates real-time sensor data visualization, Principal Component Analysis (PCA)-based fault detection, and identification of top contributing variables within an interactive user interface powered by large language models (LLMs). We evaluate the LLMs' reasoning capabilities in two scenarios: one where historical root causes are provided, and one where they are not to mimic the challenge of previously unseen faults. Experimental results using GPT-4o and o1-preview models demonstrate the system's strengths in generating plausible and actionable explanations, while also highlighting its limitations, including reliance on PCA-selected features and occasional hallucinations.

Error detection and correction are essential for ensuring robust and reliable operation in modern communication systems, particularly in complex transmission environments. However, discussions on these topics have largely been overlooked in semantic communication (SemCom), which focuses on transmitting meaning rather than symbols, leading to significant improvements in communication efficiency. Despite these advantages, semantic errors -- stemming from discrepancies between transmitted and received meanings -- present a major challenge to system reliability. This paper addresses this gap by proposing a comprehensive framework for detecting and correcting semantic errors in SemCom systems. We formally define semantic error, detection, and correction mechanisms, and identify key sources of semantic errors. To address these challenges, we develop a Gaussian process (GP)-based method for latent space monitoring to detect errors, alongside a human-in-the-loop reinforcement learning (HITL-RL) approach to optimize semantic model configurations using user feedback. Experimental results validate the effectiveness of the proposed methods in mitigating semantic errors under various conditions, including adversarial attacks, input feature changes, physical channel variations, and user preference shifts. This work lays the foundation for more reliable and adaptive SemCom systems with robust semantic error management techniques.

Recent advancements in generative AI have introduced novel prospects and practical implementations. Especially diffusion models show their strength in generating diverse and, at the same time, realistic features, positioning them well for generating counterfactual explanations for computer vision models. Answering "what if" questions of what needs to change to make an image classifier change its prediction, counterfactual explanations align well with human understanding and consequently help in making model behavior more comprehensible. Current methods succeed in generating authentic counterfactuals, but lack transparency as feature changes are not directly perceivable. To address this limitation, we introduce Concept-guided Latent Diffusion Counterfactual Explanations (CoLa-DCE). CoLa-DCE generates concept-guided counterfactuals for any classifier with a high degree of control regarding concept selection and spatial conditioning. The counterfactuals comprise an increased granularity through minimal feature changes. The reference feature visualization ensures better comprehensibility, while the feature localization provides increased transparency of "where" changed "what". We demonstrate the advantages of our approach in minimality and comprehensibility across multiple image classification models and datasets and provide insights into how our CoLa-DCE explanations help comprehend model errors like misclassification cases.

The two-stage fine-tuning (FT) method, linear probing then fine-tuning (LP-FT), consistently outperforms linear probing (LP) and FT alone in terms of accuracy for both in-distribution (ID) and out-of-distribution (OOD) data. This success is largely attributed to the preservation of pre-trained features, achieved through a near-optimal linear head obtained during LP. However, despite the widespread use of large language models, the exploration of complex architectures such as Transformers remains limited. In this paper, we analyze the training dynamics of LP-FT for classification models on the basis of the neural tangent kernel (NTK) theory. Our analysis decomposes the NTK matrix into two components, highlighting the importance of the linear head norm alongside the prediction accuracy at the start of the FT stage. We also observe a significant increase in the linear head norm during LP, stemming from training with the cross-entropy (CE) loss, which effectively minimizes feature changes. Furthermore, we find that this increased norm can adversely affect model calibration, a challenge that can be addressed by temperature scaling. Additionally, we extend our analysis with the NTK to the low-rank adaptation (LoRA) method and validate its effectiveness. Our experiments with a Transformer-based model on natural language processing tasks across multiple benchmarks confirm our theoretical analysis and demonstrate the effectiveness of LP-FT in fine-tuning language models. Code is available at https://github.com/tom4649/lp-ft_ntk.

Machine learning models are widely used in real-world applications. However, their complexity makes it often challenging to interpret the rationale behind their decisions. Counterfactual explanations (CEs) have emerged as a viable solution for generating comprehensible explanations in eXplainable Artificial Intelligence (XAI). CE provides actionable information to users on how to achieve the desired outcome with minimal modifications to the input. However, current CE algorithms usually operate within the entire feature space when optimizing changes to turn over an undesired outcome, overlooking the identification of key contributors to the outcome and disregarding the practicality of the suggested changes. In this study, we introduce a novel methodology, that is named as user feedback-based counterfactual explanation (UFCE), which addresses these limitations and aims to bolster confidence in the provided explanations. UFCE allows for the inclusion of user constraints to determine the smallest modifications in the subset of actionable features while considering feature dependence, and evaluates the practicality of suggested changes using benchmark evaluation metrics. We conducted three experiments with five datasets, demonstrating that UFCE outperforms two well-known CE methods in terms of \textit{proximity}, \textit{sparsity}, and \textit{feasibility}. Reported results indicate that user constraints influence the generation of feasible CEs.

With the advancement of generative models, the assessment of generated images becomes more and more important. Previous methods measure distances between features of reference and generated images from trained vision models. In this paper, we conduct an extensive investigation into the relationship between the representation space and input space around generated images. We first propose two measures related to the presence of unnatural elements within images: complexity, which indicates how non-linear the representation space is, and vulnerability, which is related to how easily the extracted feature changes by adversarial input changes. Based on these, we introduce a new metric to evaluating image-generative models called anomaly score (AS). Moreover, we propose AS-i (anomaly score for individual images) that can effectively evaluate generated images individually. Experimental results demonstrate the validity of the proposed approach.

Despite the success of complex machine learning algorithms, mostly justified by an outstanding performance in prediction tasks, their inherent opaque nature still represents a challenge to their responsible application. Counterfactual explanations surged as one potential solution to explain individual decision results. However, two major drawbacks directly impact their usability: (1) the isonomic view of feature changes, in which it is not possible to observe \textit{how much} each modified feature influences the prediction, and (2) the lack of graphical resources to visualize the counterfactual explanation. We introduce Counterfactual Feature (change) Importance (CFI) values as a solution: a way of assigning an importance value to each feature change in a given counterfactual explanation. To calculate these values, we propose two potential CFI methods. One is simple, fast, and has a greedy nature. The other, coined CounterShapley, provides a way to calculate Shapley values between the factual-counterfactual pair. Using these importance values, we additionally introduce three chart types to visualize the counterfactual explanations: (a) the Greedy chart, which shows a greedy sequential path for prediction score increase up to predicted class change, (b) the CounterShapley chart, depicting its respective score in a simple and one-dimensional chart, and finally (c) the Constellation chart, which shows all possible combinations of feature changes, and their impact on the model's prediction score. For each of our proposed CFI methods and visualization schemes, we show how they can provide more information on counterfactual explanations. Finally, an open-source implementation is offered, compatible with any counterfactual explanation generator algorithm. Code repository at: https://github.com/ADMAntwerp/CounterPlots