This paper describes the creation, optimization, and assessment of a question-answering (QA) model for a personalized learning assistant that uses BERT transformers customized for the Arabic language. The model was particularly finetuned on science textbooks in Palestinian curriculum. Our approach uses BERT's brilliant capabilities to automatically produce correct answers to questions in the field of science education. The model's ability to understand and extract pertinent information is improved by finetuning it using 11th and 12th grade biology book in Palestinian curriculum. This increases the model's efficacy in producing enlightening responses. Exact match (EM) and F1 score metrics are used to assess the model's performance; the results show an EM score of 20% and an F1 score of 51%. These findings show that the model can comprehend and react to questions in the context of Palestinian science book. The results demonstrate the potential of BERT-based QA models to support learning and understanding Arabic students questions.

Programming skills are typically developed through completing various hands-on exercises. Such programming problems can be contextualized to students' interests and cultural backgrounds. Prior research in educational psychology has demonstrated that context personalization of exercises stimulates learners' situational interests and positively affects their engagement. However, creating a varied and comprehensive set of programming exercises for students to practice on is a time-consuming and laborious task for computer science educators. Previous studies have shown that large language models can generate conceptually and contextually relevant programming exercises. Thus, they offer a possibility to automatically produce personalized programming problems to fit students' interests and needs. This article reports on a user study conducted in an elective introductory programming course that included contextually personalized programming exercises created with GPT-4. The quality of the exercises was evaluated by both the students and the authors. Additionally, this work investigated student attitudes towards the created exercises and their engagement with the system. The results demonstrate that the quality of exercises generated with GPT-4 was generally high. What is more, the course participants found them engaging and useful. This suggests that AI-generated programming problems can be a worthwhile addition to introductory programming courses, as they provide students with a practically unlimited pool of practice material tailored to their personal interests and educational needs.

Writing mathematical proofs has been identified as an important [1-3] and yet challenging topic [4] in computing education and mathematics education. A large body of research has shown that timely feedback is crucial to student learning [5, 6]. However, students are largely unable to receive timely feedback on written proofs due to the need to have proofs collected and hand-graded by instructors or teaching assistants. The ability to grade student proofs fully automatically with natural language processing (NLP) alleviates this need by allowing us to give students instant feedback on their proofs to let students iteratively enhance the quality of their proofs. In this paper, we propose a novel set of training methods and models capable of autograding freeform mathematical proofs, a problem at the intersection of mathematical proof education and Automatic Short Answer Grading (ASAG), by using existing NLP models and other machine learning techniques. Our proof autograder enables the development of grading systems that provide instant feedback to students without needing attention from instructors. It can also be deployed in large-scale educational platforms, allowing for more access for students. The main contributions of this paper are: Introducing the first pipeline of machine learning models capable of autograding mathematical proofs with similar accuracy to human graders Quantifying the amount of training data needed to achieve a satisfactory performance from the grading models Publishing an anonymized and labeled mathematical proof dataset that can be used in future model developments [7] Creating a set of autograded problems using the grading pipeline, and performing a user study that answers the following research questions: - Are students able to write better proofs by interacting with the autograder and the feedback it generates?

Large Language Models (LLMs) exhibit extensive knowledge about the world, but most evaluations have been limited to global or anglocentric subjects. This raises the question of how well these models perform on topics relevant to other cultures, whose presence on the web is not that prominent. To address this gap, we introduce BertaQA, a multiple-choice trivia dataset that is parallel in English and Basque. The dataset consists of a local subset with questions pertinent to the Basque culture, and a global subset with questions of broader interest. We find that state-of-the-art LLMs struggle with local cultural knowledge, even as they excel on global topics. However, we show that continued pre-training in Basque significantly improves the models' performance on Basque culture, even when queried in English. To our knowledge, this is the first solid evidence of knowledge transfer from a low-resource to a high-resource language. Our analysis sheds light on the complex interplay between language and knowledge, and reveals that some prior findings do not fully hold when reassessed on local topics. Our dataset and evaluation code are available under open licenses at https://github.com/juletx/BertaQA.

This study focuses on the locomotion capability improvement in a tendon-driven soft quadruped robot through an online adaptive learning approach. Leveraging the inverse kinematics model of the soft quadruped robot, we employ a central pattern generator to design a parametric gait pattern, and use Bayesian optimization (BO) to find the optimal parameters. Further, to address the challenges of modeling discrepancies, we implement a multi-fidelity BO approach, combining data from both simulation and physical experiments throughout training and optimization. This strategy enables the adaptive refinement of the gait pattern and ensures a smooth transition from simulation to real-world deployment for the controller. Moreover, we integrate a computational task off-loading architecture by edge computing, which reduces the onboard computational and memory overhead, to improve real-time control performance and facilitate an effective online learning process. The proposed approach successfully achieves optimal walking gait design for physical deployment with high efficiency, effectively addressing challenges related to the reality gap in soft robotics.

Automatic reading diagnosis systems can benefit both teachers for more efficient scoring of reading exercises and students for accessing reading exercises with feedback more easily. However, there are limited studies on Automatic Speech Recognition (ASR) for child speech in languages other than English, and limited research on ASR-based reading diagnosis systems. This study investigates how efficiently state-of-the-art (SOTA) pretrained ASR models recognize Dutch native children speech and manage to detect reading miscues. We found that Hubert Large finetuned on Dutch speech achieves SOTA phoneme-level child speech recognition (PER at 23.1\%), while Whisper (Faster Whisper Large-v2) achieves SOTA word-level performance (WER at 9.8\%). Our findings suggest that Wav2Vec2 Large and Whisper are the two best ASR models for reading miscue detection. Specifically, Wav2Vec2 Large shows the highest recall at 0.83, whereas Whisper exhibits the highest precision at 0.52 and an F1 score of 0.52.

The last several years saw the emergence of AI assistants for code -- multi-purpose AI-based helpers in software engineering. Their quick development makes it necessary to better understand how specifically developers are using them, why they are not using them in certain parts of their development workflow, and what needs to be improved. In this work, we carried out a large-scale survey aimed at how AI assistants are used, focusing on specific software development activities and stages. We collected opinions of 481 programmers on five broad activities: (a) implementing new features, (b) writing tests, (c) bug triaging, (d) refactoring, and (e) writing natural-language artifacts, as well as their individual stages. Our results show that usage of AI assistants varies depending on activity and stage. For instance, developers find writing tests and natural-language artifacts to be the least enjoyable activities and want to delegate them the most, currently using AI assistants to generate tests and test data, as well as generating comments and docstrings most of all. This can be a good focus for features aimed to help developers right now. As for why developers do not use assistants, in addition to general things like trust and company policies, there are fixable issues that can serve as a guide for further research, e.g., the lack of project-size context, and lack of awareness about assistants. We believe that our comprehensive and specific results are especially needed now to steer active research toward where users actually need AI assistants.

In this paper, we attempt to address the challenge of applying Neural Architecture Search (NAS) algorithms, specifically the Differentiable Architecture Search (DARTS), to long-tailed datasets where class distribution is highly imbalanced. We observe that traditional re-sampling and re-weighting techniques, which are effective in standard classification tasks, lead to performance degradation when combined with DARTS. To mitigate this, we propose a novel adaptive learning rate scheduling strategy tailored for the architecture parameters of DARTS when integrated with the Bilateral Branch Network (BBN) for handling imbalanced datasets. Our approach dynamically adjusts the learning rate of the architecture parameters based on the training epoch, preventing the disruption of well-trained representations in the later stages of training. Additionally, we explore the impact of branch mixing factors on the algorithm's performance. Through extensive experiments on the CIFAR-10 dataset with an artificially induced long-tailed distribution, we demonstrate that our method achieves comparable accuracy to using DARTS alone. And the experiment results suggest that re-sampling methods inherently harm the performance of the DARTS algorithm. Our findings highlight the importance of careful data augment when applying DNAS to imbalanced learning scenarios.

Driven by the demand for cross-sentence and large-scale relation extraction, document-level relation extraction (DocRE) has attracted increasing research interest. Despite the continuous improvement in performance, we find that existing DocRE models which initially perform well may make more mistakes when merely changing the entity names in the document, hindering the generalization to novel entity names. To this end, we systematically investigate the robustness of DocRE models to entity name variations in this work. We first propose a principled pipeline to generate entity-renamed documents by replacing the original entity names with names from Wikidata. By applying the pipeline to DocRED and Re-DocRED datasets, we construct two novel benchmarks named Env-DocRED and Env-Re-DocRED for robustness evaluation. Experimental results show that both three representative DocRE models and two in-context learned large language models consistently lack sufficient robustness to entity name variations, particularly on cross-sentence relation instances and documents with more entities. Finally, we propose an entity variation robust training method which not only improves the robustness of DocRE models but also enhances their understanding and reasoning capabilities. We further verify that the basic idea of this method can be effectively transferred to in-context learning for DocRE as well.

The customization of large language models (LLMs) for user-specified tasks gets important. However, maintaining all the customized LLMs on cloud servers incurs substantial memory and computational overheads, and uploading user data can also lead to privacy concerns. On-device LLMs can offer a promising solution by mitigating these issues. Yet, the performance of on-device LLMs is inherently constrained by the limitations of small-scaled models. To overcome these restrictions, we first propose Crayon, a novel approach for on-device LLM customization. Crayon begins by constructing a pool of diverse base adapters, and then we instantly blend them into a customized adapter without extra training. In addition, we develop a device-server hybrid inference strategy, which deftly allocates more demanding queries or non-customized tasks to a larger, more capable LLM on a server. This ensures optimal performance without sacrificing the benefits of on-device customization. We carefully craft a novel benchmark from multiple question-answer datasets, and show the efficacy of our method in the LLM customization.