The growing enrollments in computer science courses and increase in class sizes necessitate scalable, automated tutoring solutions to adequately support student learning. While Large Language Models (LLMs) like GPT-3.5 have demonstrated potential in assisting students through question-answering, educators have significant concerns about students misusing LLMs or LLMs misleading students with inaccurate answers. This paper introduces CourseAssist, a novel LLM-based tutoring system tailored for computer science education. Unlike generic LLM systems, CourseAssist leverages retrieval-augmented generation along with user intent classification and post-processing to ensure that responses align with specific course learning goals, thereby addressing the pedagogical appropriateness of LLMs in educational settings. I evaluate CourseAssist against a baseline of GPT 3.5 using a dataset of 50 question-answer pairs from a programming languages course, focusing on the criteria of usefulness, accuracy, and pedagogical appropriateness. Evaluation results show that CourseAssist significantly outperforms the baseline, demonstrating its potential to serve as an effective learning assistant. This work not only highlights the importance of deliberate design considerations in LLM-based educational tools but also opens up avenues for future research, particularly in understanding user interactions with such systems in real-world scenarios and integrating human educators into LLM-based tutoring systems.

Reinforcement learning (RL) is inherently rife with non-stationarity since the states and rewards the agent observes during training depend on its changing policy. Therefore, networks in deep RL must be capable of adapting to new observations and fitting new targets. However, previous works have observed that networks in off-policy deep value-based methods exhibit a decrease in representation rank, often correlated with an inability to continue learning or a collapse in performance. Although this phenomenon has generally been attributed to neural network learning under non-stationarity, it has been overlooked in on-policy policy optimization methods which are often thought capable of training indefinitely. In this work, we empirically study representation dynamics in Proximal Policy Optimization (PPO) on the Atari and MuJoCo environments, revealing that PPO agents are also affected by feature rank deterioration and loss of plasticity. We show that this is aggravated with stronger non-stationarity, ultimately driving the actor's performance to collapse, regardless of the performance of the critic. We draw connections between representation collapse, performance collapse, and trust region issues in PPO, and present Proximal Feature Optimization (PFO), a novel auxiliary loss, that along with other interventions shows that regularizing the representation dynamics improves the performance of PPO agents.

This paper introduces CookingSense, a descriptive collection of knowledge assertions in the culinary domain extracted from various sources, including web data, scientific papers, and recipes, from which knowledge covering a broad range of aspects is acquired. CookingSense is constructed through a series of dictionary-based filtering and language model-based semantic filtering techniques, which results in a rich knowledgebase of multidisciplinary food-related assertions. Additionally, we present FoodBench, a novel benchmark to evaluate culinary decision support systems. From evaluations with FoodBench, we empirically prove that CookingSense improves the performance of retrieval augmented language models.

Federated learning is a promising collaborative and privacy-preserving machine learning approach in data-rich smart cities. Nevertheless, the inherent heterogeneity of these urban environments presents a significant challenge in selecting trustworthy clients for collaborative model training. The usage of traditional approaches, such as the random client selection technique, poses several threats to the system's integrity due to the possibility of malicious client selection. Primarily, the existing literature focuses on assessing the trustworthiness of clients, neglecting the crucial aspect of trust in federated servers. To bridge this gap, in this work, we propose a novel framework that addresses the mutual trustworthiness in federated learning by considering the trust needs of both the client and the server. Our approach entails: (1) Creating preference functions for servers and clients, allowing them to rank each other based on trust scores, (2) Establishing a reputation-based recommendation system leveraging multiple clients to assess newly connected servers, (3) Assigning credibility scores to recommending devices for better server trustworthiness measurement, (4) Developing a trust assessment mechanism for smart devices using a statistical Interquartile Range (IQR) method, (5) Designing intelligent matching algorithms considering the preferences of both parties. Based on simulation and experimental results, our approach outperforms baseline methods by increasing trust levels, global model accuracy, and reducing non-trustworthy clients in the system.

Virtual network embedding (VNE) is an essential resource allocation task in network virtualization, aiming to map virtual network requests (VNRs) onto physical infrastructure. Reinforcement learning (RL) has recently emerged as a promising solution to this problem. However, existing RL-based VNE methods are limited by the unidirectional action design and one-size-fits-all training strategy, resulting in restricted searchability and generalizability. In this paper, we propose a FLexible And Generalizable RL framework for VNE, named FlagVNE. Specifically, we design a bidirectional action-based Markov decision process model that enables the joint selection of virtual and physical nodes, thus improving the exploration flexibility of solution space. To tackle the expansive and dynamic action space, we design a hierarchical decoder to generate adaptive action probability distributions and ensure high training efficiency. Furthermore, to overcome the generalization issue for varying VNR sizes, we propose a meta-RL-based training method with a curriculum scheduling strategy, facilitating specialized policy training for each VNR size. Finally, extensive experimental results show the effectiveness of FlagVNE across multiple key metrics. Our code is available at GitHub (https://github.com/GeminiLight/flag-vne).

Dynamic Graph Neural Networks (GNNs) combine temporal information with GNNs to capture structural, temporal, and contextual relationships in dynamic graphs simultaneously, leading to enhanced performance in various applications. As the demand for dynamic GNNs continues to grow, numerous models and frameworks have emerged to cater to different application needs. There is a pressing need for a comprehensive survey that evaluates the performance, strengths, and limitations of various approaches in this domain. This paper aims to fill this gap by offering a thorough comparative analysis and experimental evaluation of dynamic GNNs. It covers 81 dynamic GNN models with a novel taxonomy, 12 dynamic GNN training frameworks, and commonly used benchmarks. We also conduct experimental results from testing representative nine dynamic GNN models and three frameworks on six standard graph datasets. Evaluation metrics focus on convergence accuracy, training efficiency, and GPU memory usage, enabling a thorough comparison of performance across various models and frameworks. From the analysis and evaluation results, we identify key challenges and offer principles for future research to enhance the design of models and frameworks in the dynamic GNNs field.

The use of automatic short answer grading (ASAG) models may help alleviate the time burden of grading while encouraging educators to frequently incorporate open-ended items in their curriculum. However, current state-of-the-art ASAG models are large neural networks (NN) often described as "black box", providing no explanation for which characteristics of an input are important for the produced output. This inexplicable nature can be frustrating to teachers and students when trying to interpret, or learn from an automatically-generated grade. To create a powerful yet intelligible ASAG model, we experiment with a type of model called a Neural Additive Model that combines the performance of a NN with the explainability of an additive model. We use a Knowledge Integration (KI) framework from the learning sciences to guide feature engineering to create inputs that reflect whether a student includes certain ideas in their response. We hypothesize that indicating the inclusion (or exclusion) of predefined ideas as features will be sufficient for the NAM to have good predictive power and interpretability, as this may guide a human scorer using a KI rubric. We compare the performance of the NAM with another explainable model, logistic regression, using the same features, and to a non-explainable neural model, DeBERTa, that does not require feature engineering.

Natural language generation tools are powerful and effective for generating content. However, language models are known to display bias and fairness issues, making them impractical to deploy for many use cases. We here focus on how fairness issues impact automatically generated test content, which can have stringent requirements to ensure the test measures only what it was intended to measure. Specifically, we review test content generated for a large-scale standardized English proficiency test with the goal of identifying content that only pertains to a certain subset of the test population as well as content that has the potential to be upsetting or distracting to some test takers. Issues like these could inadvertently impact a test taker's score and thus should be avoided. This kind of content does not reflect the more commonly-acknowledged biases, making it challenging even for modern models that contain safeguards. We build a dataset of 601 generated texts annotated for fairness and explore a variety of methods for classification: fine-tuning, topic-based classification, and prompting, including few-shot and self-correcting prompts. We find that combining prompt self-correction and few-shot learning performs best, yielding an F1 score of 0.79 on our held-out test set, while much smaller BERT- and topic-based models have competitive performance on out-of-domain data.

The field of efficient Large Language Model (LLM) inference is rapidly evolving, presenting a unique blend of opportunities and challenges. Although the field has expanded and is vibrant, there hasn't been a concise framework that analyzes the various methods of LLM Inference to provide a clear understanding of this domain. Our survey stands out from traditional literature reviews by not only summarizing the current state of research but also by introducing a framework based on roofline model for systematic analysis of LLM inference techniques. This framework identifies the bottlenecks when deploying LLMs on hardware devices and provides a clear understanding of practical problems, such as why LLMs are memory-bound, how much memory and computation they need, and how to choose the right hardware. We systematically collate the latest advancements in efficient LLM inference, covering crucial areas such as model compression (e.g., Knowledge Distillation and Quantization), algorithm improvements (e.g., Early Exit and Mixture-of-Expert), and both hardware and system-level enhancements. Our survey stands out by analyzing these methods with roofline model, helping us understand their impact on memory access and computation. This distinctive approach not only showcases the current research landscape but also delivers valuable insights for practical implementation, positioning our work as an indispensable resource for researchers new to the field as well as for those seeking to deepen their understanding of efficient LLM deployment. The analyze tool, LLM-Viewer, is open-sourced.

Teaching programming in early childhood (4-9) to enhance computational thinking has gained popularity in the recent movement of computer science for all. However, current practices ignore some fundamental issues resulting from young children's developmental readiness, such as the sustained capability to keyboarding, the decomposition of complex tasks to small tasks, the need for intuitive mapping from abstract programming to tangible outcomes, and the limited amount of screen time exposure. To address these issues in this paper, we present a novel methodology with an AI-powered integration platform to effectively teach computational thinking for young children. The system features a hybrid pedagogy that supports both the top-down and bottom-up approach for teaching computational thinking. Young children can describe their desired task in natural language, while the system can respond with an easy-to-understand program consisting of the right level of decomposed sub-tasks. A tangible robot can immediately execute the decomposed program and demonstrate the program's outcomes to young children. The system is equipped with an intelligent chatbot that can interact with young children through natural languages, and children can speak to the chatbot to complete all the needed programming tasks, while the chatbot orchestrates the execution of the program onto the robot. This would completely eliminates the need of keyboards for young children to program. By developing such a system, we aim to make the concept of computational thinking more accessible to young children, fostering a natural understanding of programming concepts without the need of explicit programming skills. Through the interactive experience provided by the robotic agent, our system seeks to engage children in an effective manner, contributing to the field of educational technology for early childhood computer science education.