Researchers have developed an AI-powered robot they claim can beat the physical marble game Labyrinth faster than humans are capable of. Thomas Bi and Raffaello D'Andrea of ETH Zurich created CyberRunner, which combines model-based reinforcement with the dexterity required to beat a game that requires physical skill, coordination and precision. For the uninitiated, the aim of the game is to guide a marble through a maze without falling into any holes. The player controls the movement of the ball by rotating two dials, which tilt the board. A camera observes the game and an algorithm learns more about it from each attempt.

This volume contains revised versions of the papers selected for the fourth volume of the Online Handbook of Argumentation for AI (OHAAI). Previously, formal theories of argument and argument interaction have been proposed and studied, and this has led to the more recent study of computational models of argument. Argumentation, as a field within artificial intelligence (AI), is highly relevant for researchers interested in symbolic representations of knowledge and defeasible reasoning. The purpose of this handbook is to provide an open access and curated anthology for the argumentation research community. OHAAI is designed to serve as a research hub to keep track of the latest and upcoming PhD-driven research on the theory and application of argumentation in all areas related to AI.

Artificial Intelligence (AI) technologies have been applied in various domains, including early childhood education (ECE). Integration of AI educational technology is a recent significant trend in ECE. Currently, there are more and more studies of AI in ECE. To date, there is a lack of survey articles that discuss the studies of AI in ECE. In this paper, we provide an up-to-date and in-depth overview of the key AI technologies in ECE that provides a historical perspective, summarizes the representative works, outlines open questions, discusses the trends and challenges through a detailed bibliometric analysis, and provides insightful recommendations for future research. We mainly discuss the studies that apply AI-based robots and AI technologies to ECE, including improving the social interaction of children with an autism spectrum disorder. This paper significantly contributes to provide an up-to-date and in-depth survey that is suitable as introductory material for beginners to AI in ECE, as well as supplementary material for advanced users.

Interpretability for machine learning models in medical imaging (MLMI) is an important direction of research. However, there is a general sense of murkiness in what interpretability means. Why does the need for interpretability in MLMI arise? What goals does one actually seek to address when interpretability is needed? To answer these questions, we identify a need to formalize the goals and elements of interpretability in MLMI. By reasoning about real-world tasks and goals common in both medical image analysis and its intersection with machine learning, we identify five core elements of interpretability: localization, visual recognizability, physical attribution, model transparency, and actionability. From this, we arrive at a framework for interpretability in MLMI, which serves as a step-by-step guide to approaching interpretability in this context. Overall, this paper formalizes interpretability needs in the context of medical imaging, and our applied perspective clarifies concrete MLMI-specific goals and considerations in order to guide method design and improve real-world usage. Our goal is to provide practical and didactic information for model designers and practitioners, inspire developers of models in the medical imaging field to reason more deeply about what interpretability is achieving, and suggest future directions of interpretability research.

Because "out-of-the-box" large language models are capable of generating a great deal of objectionable content, recent work has focused on aligning these models in an attempt to prevent undesirable generation. While there has been some success at circumventing these measures -- so-called "jailbreaks" against LLMs -- these attacks have required significant human ingenuity and are brittle in practice. In this paper, we propose a simple and effective attack method that causes aligned language models to generate objectionable behaviors. Specifically, our approach finds a suffix that, when attached to a wide range of queries for an LLM to produce objectionable content, aims to maximize the probability that the model produces an affirmative response (rather than refusing to answer). However, instead of relying on manual engineering, our approach automatically produces these adversarial suffixes by a combination of greedy and gradient-based search techniques, and also improves over past automatic prompt generation methods. Surprisingly, we find that the adversarial prompts generated by our approach are quite transferable, including to black-box, publicly released LLMs. Specifically, we train an adversarial attack suffix on multiple prompts (i.e., queries asking for many different types of objectionable content), as well as multiple models (in our case, Vicuna-7B and 13B). When doing so, the resulting attack suffix is able to induce objectionable content in the public interfaces to ChatGPT, Bard, and Claude, as well as open source LLMs such as LLaMA-2-Chat, Pythia, Falcon, and others. In total, this work significantly advances the state-of-the-art in adversarial attacks against aligned language models, raising important questions about how such systems can be prevented from producing objectionable information. Code is available at github.com/llm-attacks/llm-attacks.

We tackle the problem of sampling from intractable high-dimensional density functions, a fundamental task that often appears in machine learning and statistics. We extend recent sampling-based approaches that leverage controlled stochastic processes to model approximate samples from these target densities. The main drawback of these approaches is that the training objective requires full trajectories to compute, resulting in sluggish credit assignment issues due to use of entire trajectories and a learning signal present only at the terminal time. In this work, we present Diffusion Generative Flow Samplers (DGFS), a sampling-based framework where the learning process can be tractably broken down into short partial trajectory segments, via parameterizing an additional "flow function". Our method takes inspiration from the theory developed for generative flow networks (GFlowNets), allowing us to make use of intermediate learning signals. Through various challenging experiments, we demonstrate that DGFS achieves more accurate estimates of the normalization constant than closely-related prior methods.

We establish explicit dynamics for neural networks whose training objective has a regularising term that constrains the parameters to remain close to their initial value. This keeps the network in a lazy training regime, where the dynamics can be linearised around the initialisation. The standard neural tangent kernel (NTK) governs the evolution during the training in the infinite-width limit, although the regularisation yields an additional term appears in the differential equation describing the dynamics. This setting provides an appropriate framework to study the evolution of wide networks trained to optimise generalisation objectives such as PAC-Bayes bounds, and hence potentially contribute to a deeper theoretical understanding of such networks.

This research aims to demonstrate that AI can function not only as a tool for learning, but also as an intelligent agent with which humans can engage in collaborative learning (CL) to change epistemic practices in science classrooms. We adopted a design and development research approach, following the Analysis, Design, Development, Implementation and Evaluation (ADDIE) model, to prototype a tangible instructional system called Collaborative Learning with AI Speakers (CLAIS). The CLAIS system is designed to have 3-4 human learners join an AI speaker to form a small group, where humans and AI are considered as peers participating in the Jigsaw learning process. The development was carried out using the NUGU AI speaker platform. The CLAIS system was successfully implemented in a Science Education course session with 15 pre-service elementary science teachers. The participants evaluated the CLAIS system through mixed methods surveys as teachers, learners, peers, and users. Quantitative data showed that the participants' Intelligent-Technological, Pedagogical, And Content Knowledge was significantly increased after the CLAIS session, the perception of the CLAIS learning experience was positive, the peer assessment on AI speakers and human peers was different, and the user experience was ambivalent. Qualitative data showed that the participants anticipated future changes in the epistemic process in science classrooms, while acknowledging technical issues such as speech recognition performance and response latency. This study highlights the potential of Human-AI Collaboration for knowledge co-construction in authentic classroom settings and exemplify how AI could shape the future landscape of epistemic practices in the classroom.

The rapid expansion of Learning Analytics (LA) and Artificial Intelligence in Education (AIED) offers new scalable, data-intensive systems but also raises concerns about data privacy and agency. Excluding stakeholders -- like students and teachers -- from the design process can potentially lead to mistrust and inadequately aligned tools. Despite a shift towards human-centred design in recent LA and AIED research, there remain gaps in our understanding of the importance of human control, safety, reliability, and trustworthiness in the design and implementation of these systems. We conducted a systematic literature review to explore these concerns and gaps. We analysed 108 papers to provide insights about i) the current state of human-centred LA/AIED research; ii) the extent to which educational stakeholders have contributed to the design process of human-centred LA/AIED systems; iii) the current balance between human control and computer automation of such systems; and iv) the extent to which safety, reliability and trustworthiness have been considered in the literature. Results indicate some consideration of human control in LA/AIED system design, but limited end-user involvement in actual design. Based on these findings, we recommend: 1) carefully balancing stakeholders' involvement in designing and deploying LA/AIED systems throughout all design phases, 2) actively involving target end-users, especially students, to delineate the balance between human control and automation, and 3) exploring safety, reliability, and trustworthiness as principles in future human-centred LA/AIED systems.

Motivated by recent work on lifelong learning applications for language models (LMs) of code, we introduce CodeLL, a lifelong learning dataset focused on code changes. Our contribution addresses a notable research gap marked by the absence of a long-term temporal dimension in existing code change datasets, limiting their suitability in lifelong learning scenarios. In contrast, our dataset aims to comprehensively capture code changes across the entire release history of open-source software repositories. In this work, we introduce an initial version of CodeLL, comprising 71 machine-learning-based projects mined from Software Heritage. This dataset enables the extraction and in-depth analysis of code changes spanning 2,483 releases at both the method and API levels. CodeLL enables researchers studying the behaviour of LMs in lifelong fine-tuning settings for learning code changes. Additionally, the dataset can help studying data distribution shifts within software repositories and the evolution of API usages over time.