Most existing work on event extraction has focused on sentence-level texts and presumes the identification of a trigger-span -- a word or phrase in the input that evokes the occurrence of an event of interest. Event arguments are then extracted with respect to the trigger. Indeed, triggers are treated as integral to, and trigger detection as an essential component of, event extraction. In this paper, we provide the first investigation of the role of triggers for the more difficult and much less studied task of document-level event extraction. We analyze their usefulness in multiple end-to-end and pipelined neural event extraction models for three document-level event extraction datasets, measuring performance using triggers of varying quality (human-annotated, LLM-generated, keyword-based, and random). Our research shows that trigger effectiveness varies based on the extraction task's characteristics and data quality, with basic, automatically-generated triggers serving as a viable alternative to human-annotated ones. Furthermore, providing detailed event descriptions to the extraction model helps maintain robust performance even when trigger quality degrades. Perhaps surprisingly, we also find that the mere existence of trigger input, even random ones, is important for prompt-based LLM approaches to the task.

Explanations can improve subjective perception (Bertrand et al., 2023), In recent years, AI has gained substantial attention for but also might increase cognitive load (Ghai et al., their increasingly sophisticated performance in various 2020; Herm, 2023; You et al., 2022) and reduce efficiency applications (Albrecht, 2016; Barredo Arrieta et al., (Lai et al., 2023b). This has led to a situation 2020; MacCarthy, 2019; Rong et al., 2022). However, where users often engage superficially with explanations their significant limitation compared to simpler methods and develop an overreliance on AI (Bansal et al., is their commonly opaque "black box" nature, 2021; Buçinca et al., 2021; Chen et al., 2023; Chromik making it difficult to understand how inputs generate et al., 2021), shifting from the original problem of underreliance.

Machine unlearning in neural information retrieval (IR) systems requires removing specific data whilst maintaining model performance. Applying existing machine unlearning methods to IR may compromise retrieval effectiveness or inadvertently expose unlearning actions due to the removal of particular items from the retrieved results presented to users. We formalise corrective unranking, which extends machine unlearning in (neural) IR context by integrating substitute documents to preserve ranking integrity, and propose a novel teacher-student framework, Corrective unRanking Distillation (CuRD), for this task. CuRD (1) facilitates forgetting by adjusting the (trained) neural IR model such that its output relevance scores of to-be-forgotten samples mimic those of low-ranking, non-retrievable samples; (2) enables correction by fine-tuning the relevance scores for the substitute samples to match those of corresponding to-be-forgotten samples closely; (3) seeks to preserve performance on samples that are not targeted for forgetting. We evaluate CuRD on four neural IR models (BERTcat, BERTdot, ColBERT, PARADE) using MS MARCO and TREC CAR datasets. Experiments with forget set sizes from 1 % and 20 % of the training dataset demonstrate that CuRD outperforms seven state-of-the-art baselines in terms of forgetting and correction while maintaining model retention and generalisation capabilities.

Machine unlearning is new emerged technology that removes a subset of the training data from a trained model without affecting the model performance on the remaining data. This topic is becoming increasingly important in protecting user privacy and eliminating harmful or outdated data. The key challenge lies in effectively and efficiently unlearning specific information without compromising the model's utility on the retained data. For the pre-trained models, fine-tuning is an important way to achieve the unlearning target. Previous work typically fine-tuned the entire model's parameters, which incurs significant computation costs. In addition, the fine-tuning process may cause shifts in the intermediate layer features, affecting the model's overall utility. In this work, we propose a novel and efficient machine unlearning method on pre-trained models. We term the method as Residual Feature Alignment Unlearning. Specifically, we leverage LoRA (Low-Rank Adaptation) to decompose the model's intermediate features into pre-trained features and residual features. By adjusting the residual features, we align the unlearned model with the pre-trained model at the intermediate feature level to achieve both unlearning and remaining targets. The method aims to learn the zero residuals on the retained set and shifted residuals on the unlearning set. Extensive experiments on numerous datasets validate the effectiveness of our approach.

Society is increasingly relying on predictive models in fields like criminal justice, credit risk management, or hiring. To prevent such automated systems from discriminating against people belonging to certain groups, fairness measures have become a crucial component in socially relevant applications of machine learning. However, existing fairness measures have been designed to assess the bias between predictions for protected groups without considering the imbalance in the classes of the target variable. Current research on the potential effect of class imbalance on fairness focuses on practical applications rather than dataset-independent measure properties. In this paper, we study the general properties of fairness measures for changing class and protected group proportions. For this purpose, we analyze the probability mass functions of six of the most popular group fairness measures. We also measure how the probability of achieving perfect fairness changes for varying class imbalance ratios. Moreover, we relate the dataset-independent properties of fairness measures described in this paper to classifier fairness in real-life tasks. Our results show that measures such as Equal Opportunity and Positive Predictive Parity are more sensitive to changes in class imbalance than Accuracy Equality. These findings can help guide researchers and practitioners in choosing the most appropriate fairness measures for their classification problems.

Early fault detection and timely maintenance scheduling can significantly mitigate operational risks in NPPs and enhance the reliability of operator decision-making. Therefore, it is necessary to develop an efficient Prognostics and Health Management (PHM) multi-step prediction model for predicting of system health status and prompt execution of maintenance operations. In this study, we propose a novel predictive model that integrates reinforcement learning with Long Short-Term Memory (LSTM) neural networks and the Expert Fuzzy Evaluation Method. The model is validated using parameter data for 20 different breach sizes in the Main Steam Line Break (MSLB) accident condition of the CPR1000 pressurized water reactor simulation model and it demonstrates a remarkable capability in accurately forecasting NPP parameter changes up to 128 steps ahead (with a time interval of 10 seconds per step, i.e., 1280 seconds), thereby satisfying the temporal advance requirement for fault prognostics in NPPs. Furthermore, this method provides an effective reference solution for PHM applications such as anomaly detection and remaining useful life prediction.

From prehistoric encirclement for hunting to GPS orbiting the earth for positioning, target encirclement has numerous real world applications. However, encircling multiple non-cooperative targets in GPS-denied environments remains challenging. In this work, multiple targets encirclement by using a minimum of two tasking agents, is considered where the relative distance measurements between the agents and the targets can be obtained by using onboard sensors. Based on the measurements, the center of all the targets is estimated directly by a fuzzy wavelet neural network (FWNN) and the least squares fit method. Then, a new distributed anti-synchronization controller (DASC) is designed so that the two tasking agents are able to encircle all targets while staying opposite to each other. In particular, the radius of the desired encirclement trajectory can be dynamically determined to avoid potential collisions between the two agents and all targets. Based on the Lyapunov stability analysis method, the convergence proofs of the neural network prediction error, the target-center position estimation error, and the controller error are addressed respectively. Finally, both numerical simulations and UAV flight experiments are conducted to demonstrate the validity of the encirclement algorithms. The flight tests recorded video and other simulation results can be found in https://youtu.be/B8uTorBNrl4.

Current large language models (LLM) provide a strong foundation for large-scale user-oriented natural language tasks. Many users can easily inject adversarial text or instructions through the user interface, thus causing LLM model security challenges like the language model not giving the correct answer. Although there is currently a large amount of research on black-box attacks, most of these black-box attacks use random and heuristic strategies. It is unclear how these strategies relate to the success rate of attacks and thus effectively improve model robustness. To solve this problem, we propose our target-driven black-box attack method to maximize the KL divergence between the conditional probabilities of the clean text and the attack text to redefine the attack's goal. We transform the distance maximization problem into two convex optimization problems based on the attack goal to solve the attack text and estimate the covariance. Furthermore, the projected gradient descent algorithm solves the vector corresponding to the attack text. Our target-driven black-box attack approach includes two attack strategies: token manipulation and misinformation attack. Experimental results on multiple Large Language Models and datasets demonstrate the effectiveness of our attack method.

This paper presents a novel feature selection method leveraging the Wasserstein distance to improve feature selection in machine learning. Unlike traditional methods based on correlation or Kullback-Leibler (KL) divergence, our approach uses the Wasserstein distance to assess feature similarity, inherently capturing class relationships and making it robust to noisy labels. We introduce a Markov blanket-based feature selection algorithm and demonstrate its effectiveness. Our analysis shows that the Wasserstein distance-based feature selection method effectively reduces the impact of noisy labels without relying on specific noise models. We provide a lower bound on its effectiveness, which remains meaningful even in the presence of noise. Experimental results across multiple datasets demonstrate that our approach consistently outperforms traditional methods, particularly in noisy settings.

Investigation of students' perceptions and opinions on the use of generative artificial intelligence (GenAI) in education is a topic gaining much interest. Studies addressing this are typically conducted with large heterogeneous groups, at one moment in time. However, how students perceive and use GenAI tools can potentially depend on many factors, including their background knowledge, familiarity with the tools, and the learning goals and policies of the courses they are taking. In this study we explore how students following computing courses use GenAI for programming-related tasks across different programs and courses: Bachelor and Master, in courses in which learning programming is the learning goal, courses that require programming as a means to achieve another goal, and in courses in which programming is optional, but can be useful. We are also interested in changes over time, since GenAI capabilities are changing at a fast pace, and users are adopting GenAI increasingly. We conducted three consecutive surveys (fall `23, winter `23, and spring `24) among students of all computing programs of a large European research university. We asked questions on the use in education, ethics, and job prospects, and we included specific questions on the (dis)allowed use of GenAI tools in the courses they were taking at the time. We received 264 responses, which we quantitatively and qualitatively analyzed, to find out how students have employed GenAI tools across 59 different computing courses, and whether the opinion of an average student about these tools evolves over time. Our study contributes to the emerging discussion of how to differentiate GenAI use across different courses, and how to align its use with the learning goals of a computing course.