We develop models to classify desirable evidence and desirable reasoning revisions in student argumentative writing. We explore two ways to improve classifier performance - using the essay context of the revision, and using the feedback students received before the revision. We perform both intrinsic and extrinsic evaluation for each of our models and report a qualitative analysis. Our results show that while a model using feedback information improves over a baseline model, models utilizing context - either alone or with feedback - are the most successful in identifying desirable revisions.

The rise of Artificial Intelligence (AI) technology and its impact on education has been a topic of growing concern in recent years. The new generation AI systems such as chatbots have become more accessible on the Internet and stronger in terms of capabilities. The use of chatbots, particularly ChatGPT, for generating academic essays at schools and colleges has sparked fears among scholars. This study aims to explore the originality of contents produced by one of the most popular AI chatbots, ChatGPT. To this end, two popular plagiarism detection tools were used to evaluate the originality of 50 essays generated by ChatGPT on various topics. Our results manifest that ChatGPT has a great potential to generate sophisticated text outputs without being well caught by the plagiarism check software. In other words, ChatGPT can create content on many topics with high originality as if they were written by someone. These findings align with the recent concerns about students using chatbots for an easy shortcut to success with minimal or no effort. Moreover, ChatGPT was asked to verify if the essays were generated by itself, as an additional measure of plagiarism check, and it showed superior performance compared to the traditional plagiarism-detection tools. The paper discusses the need for institutions to consider appropriate measures to mitigate potential plagiarism issues and advise on the ongoing debate surrounding the impact of AI technology on education. Further implications are discussed in the paper.

Recently, Language Models (LMs) instruction-tuned on multiple tasks, also known as multitask-prompted fine-tuning (MT), have shown the capability to generalize to unseen tasks. Previous work has shown that scaling the number of training tasks is the key component in making stronger MT LMs. In this work, we report an unexpected finding that an expert LM fine-tuned on just a single task can outperform an MT LM trained with 300+ different tasks on 11 different unseen datasets and on 13 datasets of the BIG-bench benchmark by a mean accuracy of 3.20% and 1.29%, respectively. This finding casts doubt on the previously held belief that simply scaling the number of tasks makes stronger MT LMs. Leveraging this finding, we further show that this distributed approach of training a separate expert LM per training task instead of a single MT LM for zero-shot inference possesses many benefits including (1) avoiding negative task transfer that often occurs during instruction tuning, (2) being able to continually learn new tasks without having to re-train on previous tasks to avoid catastrophic forgetting, and (3) showing compositional capabilities when merging individual experts together. The code is available at https://github.com/joeljang/ELM.

We consider the problem of identifying a minimal subset of training data $\mathcal{S}_t$ such that if the instances comprising $\mathcal{S}_t$ had been removed prior to training, the categorization of a given test point $x_t$ would have been different. Identifying such a set may be of interest for a few reasons. First, the cardinality of $\mathcal{S}_t$ provides a measure of robustness (if $|\mathcal{S}_t|$ is small for $x_t$, we might be less confident in the corresponding prediction), which we show is correlated with but complementary to predicted probabilities. Second, interrogation of $\mathcal{S}_t$ may provide a novel mechanism for contesting a particular model prediction: If one can make the case that the points in $\mathcal{S}_t$ are wrongly labeled or irrelevant, this may argue for overturning the associated prediction. Identifying $\mathcal{S}_t$ via brute-force is intractable. We propose comparatively fast approximation methods to find $\mathcal{S}_t$ based on influence functions, and find that -- for simple convex text classification models -- these approaches can often successfully identify relatively small sets of training examples which, if removed, would flip the prediction.

Dianxin Luan, Student Member, IEEE, John Thompson, Fellow, IEEE Institute for Digital Communications, School of Engineering, University of Edinburgh, Edinburgh, EH9 3JL, UK Email address: Dianxin.Luan@ed.ac.uk, john.thompson@ed.ac.uk Abstract In this paper, we propose an encoder-decoder neural architecture (called Channelformer) to achieve improved channel estimation for orthogonal frequency-division multiplexing (OFDM) waveforms in downlink scenarios. The self-attention mechanism is employed to achieve input precoding for the input features before processing them in the decoder. In particular, we implement multi-head attention in the encoder and a residual convolutional neural architecture as the decoder, respectively. We also employ a customized weight-level pruning to slim the trained neural network with a fine-tuning process, which reduces the computational complexity significantly to realize a low complexity and low latency solution. This enables reductions of up to 70% in the parameters, while maintaining an almost identical performance compared with the complete Channelformer. We also propose an effective online training method based on the fifth generation (5G) new radio (NR) configuration for the modern communication systems, which only needs the available information at the receiver for online training. Using industrial standard channel models, the simulations of attention-based solutions show superior estimation performance compared with other candidate neural network methods for channel estimation. For fifth generation (5G) wireless communication systems and beyond, the orthogonal frequency division multiplexing (OFDM) baseband waveform will be retained [1], which requires precise channel state information in order to compensate for the channel distortion and provide robust communication [2]. Conventional channel estimation methods are the least-squares (LS) and minimum mean squared error (MMSE) approaches [3]. However, with the development of modern communication systems, the LS method cannot achieve precise estimation and the implementation of the MMSE method is challenging as the perfect and complete channel statistics cannot be accessed accurately in advance. Moreover, conventional channel estimation solutions [4] [5] also cannot achieve sufficient performance. Meanwhile, artificial intelligence is impacting on the optimization and configuration of 6G [6]. It motivates the researchers in the field of wireless channel estimation to explore neural network solutions for improved performance [7] [8] [9] [10]. Compared with the conventional methods which aim to find the closed-form expression, neural network methods are typical datadriven methods aiming for a satisfactory and local optimum solution.

Representing code changes as numeric feature vectors, i.e., code change representations, is usually an essential step to automate many software engineering tasks related to code changes, e.g., commit message generation and just-in-time defect prediction. Intuitively, the quality of code change representations is crucial for the effectiveness of automated approaches. Prior work on code changes usually designs and evaluates code change representation approaches for a specific task, and little work has investigated code change encoders that can be used and jointly trained on various tasks. To fill this gap, this work proposes a novel Code Change Representation learning approach named CCRep, which can learn to encode code changes as feature vectors for diverse downstream tasks. Specifically, CCRep regards a code change as the combination of its before-change and after-change code, leverages a pre-trained code model to obtain high-quality contextual embeddings of code, and uses a novel mechanism named query back to extract and encode the changed code fragments and make them explicitly interact with the whole code change. To evaluate CCRep and demonstrate its applicability to diverse code-change-related tasks, we apply it to three tasks: commit message generation, patch correctness assessment, and just-in-time defect prediction. Experimental results show that CCRep outperforms the state-of-the-art techniques on each task.

Writing is a complex process at the center of much of modern human activity. Despite it appears to be a linear process, writing conceals many highly non-linear processes. Previous research has focused on three phases of writing: planning, translation and transcription, and revision. While research has shown these are non-linear, they are often treated linearly when measured. Here, we introduce measures to detect and quantify subcycles of planning (exploration) and translation (exploitation) during the writing process. We apply these to a novel dataset that recorded the creation of a text in all its phases, from early attempts to the finishing touches on a final version. This dataset comes from a series of writing workshops in which, through innovative versioning software, we were able to record all the steps in the construction of a text. More than 60 junior researchers in science wrote a scientific essay intended for a general readership. We recorded each essay as a writing cloud, defined as a complex topological structure capturing the history of the essay itself. Through this unique dataset of writing clouds, we expose a representation of the writing process that quantifies its complexity and the writer's efforts throughout the draft and through time. Interestingly, this representation highlights the phases of "translation flow", where authors improve existing ideas, and exploration, where creative deviations appear as the writer returns to the planning phase. These turning points between translation and exploration become rarer as the writing process progresses and the author approaches the final version. Our results and the new measures introduced have the potential to foster the discussion about the non-linear nature of writing and support the development of tools that can support more creative and impactful writing processes.

Learning from non-stationary data streams is a research direction that gains increasing interest as more data in form of streams becomes available, for example from social media, smartphones, or industrial process monitoring. Most approaches assume that the ground truth of the samples becomes available (possibly with some delay) and perform supervised online learning in the test-then-train scheme. While this assumption might be valid in some scenarios, it does not apply to all settings. In this work, we focus on scarcely labeled data streams and explore the potential of self-labeling in gradually drifting data streams. We formalize this setup and propose a novel online $k$-nn classifier that combines self-labeling and demand-based active learning.

Abstract--This paper's main goal is to provide an attacker's The dataset was compiled to look at potential applications as current or past employees, and have inside knowledge of the of brainwave signals for spotting insider threats in the business's security protocols, customer information, and workplace. The Emotiv Insight 5 channels were the tool used computer systems. To assess human emotions and acts, speech to collect the data. Information from 17 people who gave their [1] and facial expression [2] data were employed traditionally. On the other hand, EEG The four risk categories--High-Risk, Medium-Risk, Low-signals [3] have been utilized in recent years to assess a Risk, and Normal--found in the risk matrix were used to person's emotional state to prevent potential industrial insider classify each signal for a captured image, and each signal was assaults because people cannot conceal or manipulate their then given the appropriate label.

We consider the problem of learning the dynamics of a linear system when one has access to data generated by an auxiliary system that shares similar (but not identical) dynamics, in addition to data from the true system. We use a weighted least squares approach, and provide a finite sample error bound of the learned model as a function of the number of samples and various system parameters from the two systems as well as the weight assigned to the auxiliary data. We show that the auxiliary data can help to reduce the intrinsic system identification error due to noise, at the price of adding a portion of error that is due to the differences between the two system models. We further provide a data-dependent bound that is computable when some prior knowledge about the systems is available. This bound can also be used to determine the weight that should be assigned to the auxiliary data during the model training stage.