Despite impressive advancements in multilingual corpora collection and model training, developing large-scale deployments of multilingual models still presents a significant challenge. This is particularly true for language tasks that are culture-dependent. One such example is the area of multilingual sentiment analysis, where affective markers can be subtle and deeply ensconced in culture. This work presents the most extensive open massively multilingual corpus of datasets for training sentiment models. The corpus consists of 79 manually selected datasets from over 350 datasets reported in the scientific literature based on strict quality criteria. The corpus covers 27 languages representing 6 language families. Datasets can be queried using several linguistic and functional features. In addition, we present a multi-faceted sentiment classification benchmark summarizing hundreds of experiments conducted on different base models, training objectives, dataset collections, and fine-tuning strategies.

Since adaptive learning comes in many shapes and sizes, it is crucial to find out which adaptations can be meaningful for which areas of learning. Our work presents the result of an experiment conducted on an online platform for the acquisition of German spelling skills. We compared the traditional online learning platform to three different adaptive versions of the platform that implement machine learning-based student-facing interventions that show the personalized solution probability. We evaluate the different interventions with regard to the error rate, the number of early dropouts, and the users competency. Our results show that the number of mistakes decreased in comparison to the control group. Additionally, an increasing number of dropouts was found. We did not find any significant effects on the users competency. We conclude that student-facing adaptive learning environments are effective in improving a persons error rate and should be chosen wisely to have a motivating impact.

Large-scale language models, like ChatGPT, have garnered significant media attention and stunned the public with their remarkable capacity for generating coherent text from short natural language prompts. In this paper, we aim to conduct a systematic inspection of ChatGPT's performance in two controllable generation tasks, with respect to ChatGPT's ability to adapt its output to different target audiences (expert vs. layman) and writing styles (formal vs. informal). Additionally, we evaluate the faithfulness of the generated text, and compare the model's performance with human-authored texts. Our findings indicate that the stylistic variations produced by humans are considerably larger than those demonstrated by ChatGPT, and the generated texts diverge from human samples in several characteristics, such as the distribution of word types. Moreover, we observe that ChatGPT sometimes incorporates factual errors or hallucinations when adapting the text to suit a specific style.

Despite extraordinary progress, current machine learning systems have been shown to be brittle against adversarial examples: seemingly innocuous but carefully crafted perturbations of test examples that cause machine learning predictors to misclassify. Can we learn predictors robust to adversarial examples? and how? There has been much empirical interest in this contemporary challenge in machine learning, and in this thesis, we address it from a theoretical perspective. In this thesis, we explore what robustness properties can we hope to guarantee against adversarial examples and develop an understanding of how to algorithmically guarantee them. We illustrate the need to go beyond traditional approaches and principles such as empirical risk minimization and uniform convergence, and make contributions that can be categorized as follows: (1) introducing problem formulations capturing aspects of emerging practical challenges in robust learning, (2) designing new learning algorithms with provable robustness guarantees, and (3) characterizing the complexity of robust learning and fundamental limitations on the performance of any algorithm.

We consider the problem of fair column subset selection. In particular, we assume that two groups are present in the data, and the chosen column subset must provide a good approximation for both, relative to their respective best rank-k approximations. We show that this fair setting introduces significant challenges: in order to extend known results, one cannot do better than the trivial solution of simply picking twice as many columns as the original methods. We adopt a known approach based on deterministic leverage-score sampling, and show that merely sampling a subset of appropriate size becomes NP-hard in the presence of two groups. Whereas finding a subset of two times the desired size is trivial, we provide an efficient algorithm that achieves the same guarantees with essentially 1.5 times that size. We validate our methods through an extensive set of experiments on real-world data.

Recent works have shown that chain-of-thought (CoT) prompting can elicit language models to solve complex reasoning tasks, step-by-step. However, prompt-based CoT methods are dependent on very large models such as GPT-3 175B which are prohibitive to deploy at scale. In this paper, we use these large models as reasoning teachers to enable complex reasoning in smaller models and reduce model size requirements by several orders of magnitude. We propose Fine-tune-CoT, a method that generates reasoning samples from very large teacher models to fine-tune smaller models. We evaluate our method on a wide range of public models and complex tasks. We find that Fine-tune-CoT enables substantial reasoning capability in small models, far outperforming prompt-based baselines and even the teacher model in many tasks. Additionally, we extend our method by leveraging the teacher model's ability to generate multiple distinct rationales for each original sample. Enriching the fine-tuning data with such diverse reasoning results in a substantial performance boost across datasets, even for very small models. We conduct ablations and sample studies to understand the emergence of reasoning capabilities of student models. Our code implementation and data are available at https://github.com/itsnamgyu/reasoning-teacher.

A major goal of artificial intelligence (AI) is to create an agent capable of acquiring a general understanding of the world. Such an agent would require the ability to continually accumulate and build upon its knowledge as it encounters new experiences. Lifelong or continual learning addresses this setting, whereby an agent faces a continual stream of problems and must strive to capture the knowledge necessary for solving each new task it encounters. If the agent is capable of accumulating knowledge in some form of compositional representation, it could then selectively reuse and combine relevant pieces of knowledge to construct novel solutions. Despite the intuitive appeal of this simple idea, the literatures on lifelong learning and compositional learning have proceeded largely separately. In an effort to promote developments that bridge between the two fields, this article surveys their respective research landscapes and discusses existing and future connections between them.

Intelligent learning diagnosis is a critical engine of intelligent tutoring systems, which aims to estimate learners' current knowledge mastery status and predict their future learning performance. The significant challenge with traditional learning diagnosis methods is the inability to balance diagnostic accuracy and interpretability. Although the existing psychometric-based learning diagnosis methods provide some domain interpretation through cognitive parameters, they have insufficient modeling capability with a shallow structure for large-scale learning data. While the deep learning-based learning diagnosis methods have improved the accuracy of learning performance prediction, their inherent black-box properties lead to a lack of interpretability, making their results untrustworthy for educational applications. To settle the above problem, the proposed unified interpretable intelligent learning diagnosis (UIILD) framework, which benefits from the powerful representation learning ability of deep learning and the interpretability of psychometrics, achieves a better performance of learning prediction and provides interpretability from three aspects: cognitive parameters, learner-resource response network, and weights of self-attention mechanism. Within the proposed framework, this paper presents a two-channel learning diagnosis mechanism LDM-ID as well as a three-channel learning diagnosis mechanism LDM-HMI. Experiments on two real-world datasets and a simulation dataset show that our method has higher accuracy in predicting learners' performances compared with the state-of-the-art models, and can provide valuable educational interpretability for applications such as precise learning resource recommendation and personalized learning tutoring in intelligent tutoring systems.

I spent the best part of the 2010s working in new media, which – if you enjoyed being repeatedly laid off and then being inundated with jeering messages inveigling you to "learn to code" because your industry was doomed – was a great big laugh. Eventually, the fun began to wear off and in an act of subversive defiance (or cowardly resignation), I took their goading advice, learned to code and pivoted to what I'd hoped would be a far more secure career in "web development", only for recent advances in AI to supposedly render coding jobs a waste of time, too. It seems I have accidentally timed my career change to coincide with a mass rollout of AI chatbots that have also learned to code, and that are – in many respects – already far better at it than me. Code can appear alarming to the uninitiated: inscrutable "languages" that mostly read like a calculator having a stroke, but, according to AI's most fervent evangelists, they no longer need represent any barrier at all. Why bother wrapping your head around the needlessly convoluted nerdspeak required to display white text on a black background, when you can now simply ask a chatbot to do this in layperson's terms and it will promptly serve up your code, complete with instructions?

Generative Language Models (GLMs) have the potential to significantly shape our linguistic landscape due to their expansive use in various digital applications. However, this widespread adoption might inadvertently trigger a self-reinforcement learning cycle that can amplify existing linguistic biases. This paper explores the possibility of such a phenomenon, where the initial biases in GLMs, reflected in their generated text, can feed into the learning material of subsequent models, thereby reinforcing and amplifying these biases. Moreover, the paper highlights how the pervasive nature of GLMs might influence the linguistic and cognitive development of future generations, as they may unconsciously learn and reproduce these biases. The implications of this potential self-reinforcement cycle extend beyond the models themselves, impacting human language and discourse. The advantages and disadvantages of this bias amplification are weighed, considering educational benefits and ease of future GLM learning against threats to linguistic diversity and dependence on initial GLMs. This paper underscores the need for rigorous research to understand and address these issues. It advocates for improved model transparency, bias-aware training techniques, development of methods to distinguish between human and GLM-generated text, and robust measures for fairness and bias evaluation in GLMs. The aim is to ensure the effective, safe, and equitable use of these powerful technologies, while preserving the richness and diversity of human language.