Large language models (LLMs) have demonstrated exceptional capabilities in planning and tool utilization as autonomous agents, but few have been developed for medical problem-solving. We propose EHRAgent1, an LLM agent empowered with a code interface, to autonomously generate and execute code for complex clinical tasks within electronic health records (EHRs). First, we formulate an EHR question-answering task into a tool-use planning process, efficiently decomposing a complicated task into a sequence of manageable actions. By integrating interactive coding and execution feedback, EHRAgent learns from error messages and improves the originally generated code through iterations. Furthermore, we enhance the LLM agent by incorporating long-term memory, which allows EHRAgent to effectively select and build upon the most relevant successful cases from past experiences. Experiments on two real-world EHR datasets show that EHRAgent outperforms the strongest LLM agent baseline by 36.48% and 12.41%, respectively. EHRAgent leverages the emerging few-shot learning capabilities of LLMs, enabling autonomous code generation and execution to tackle complex clinical tasks with minimal demonstrations.

Robotic arms, integral in domestic care for individuals with motor impairments, enable them to perform Activities of Daily Living (ADLs) independently, reducing dependence on human caregivers. These collaborative robots require users to manage multiple Degrees-of-Freedom (DoFs) for tasks like grasping and manipulating objects. Conventional input devices, typically limited to two DoFs, necessitate frequent and complex mode switches to control individual DoFs. Modern adaptive controls with feed-forward multi-modal feedback reduce the overall task completion time, number of mode switches, and cognitive load. Despite the variety of input devices available, their effectiveness in adaptive settings with assistive robotics has yet to be thoroughly assessed. This study explores three different input devices by integrating them into an established XR framework for assistive robotics, evaluating them and providing empirical insights through a preliminary study for future developments.

In the rapidly evolving domain of Natural Language Generation (NLG) evaluation, introducing Large Language Models (LLMs) has opened new avenues for assessing generated content quality, e.g., coherence, creativity, and context relevance. This survey aims to provide a thorough overview of leveraging LLMs for NLG evaluation, a burgeoning area that lacks a systematic analysis. We propose a coherent taxonomy for organizing existing LLM-based evaluation metrics, offering a structured framework to understand and compare these methods. Our detailed exploration includes critically assessing various LLM-based methodologies, as well as comparing their strengths and limitations in evaluating NLG outputs. By discussing unresolved challenges, including bias, robustness, domain-specificity, and unified evaluation, this survey seeks to offer insights to researchers and advocate for fairer and more advanced NLG evaluation techniques.

We identify and solve a hidden-layer model that is analytically tractable at any finite width and whose limits exhibit both the kernel phase and the feature learning phase. We analyze the phase diagram of this model in all possible limits of common hyperparameters including width, layer-wise learning rates, scale of output, and scale of initialization. We apply our result to analyze how and when feature learning happens in both infinite and finite-width models. Three prototype mechanisms of feature learning are identified: (1) learning by alignment, (2) learning by disalignment, and (3) learning by rescaling. In sharp contrast, neither of these mechanisms is present when the model is in the kernel regime. This discovery explains why large initialization often leads to worse performance. Lastly, we empirically demonstrate that discoveries we made for this analytical model also appear in nonlinear networks in real tasks.

LLMs have demonstrated remarkable capability for understanding semantics, but they often struggle with understanding pragmatics. To demonstrate this fact, we release a Pragmatics Understanding Benchmark (PUB) dataset consisting of fourteen tasks in four pragmatics phenomena, namely, Implicature, Presupposition, Reference, and Deixis. We curated high-quality test sets for each task, consisting of Multiple Choice Question Answers (MCQA). PUB includes a total of 28k data points, 6.1k of which have been created by us, and the rest are adapted from existing datasets. We evaluated nine models varying in the number of parameters and type of training. Our study indicates that fine-tuning for instruction-following and chat significantly enhances the pragmatics capabilities of smaller language models. However, for larger models, the base versions perform comparably with their chat-adapted counterparts. Additionally, there is a noticeable performance gap between human capabilities and model capabilities. Furthermore, unlike the consistent performance of humans across various tasks, the models demonstrate variability in their proficiency, with performance levels fluctuating due to different hints and the complexities of tasks within the same dataset. Overall, the benchmark aims to provide a comprehensive evaluation of LLM's ability to handle real-world language tasks that require pragmatic reasoning.

Design patterns (DPs) are recognised as a good practice in software development. However, the lack of appropriate documentation often hampers traceability, and their benefits are blurred among thousands of lines of code. Automatic methods for DP detection have become relevant but are usually based on the rigid analysis of either software metrics or specific properties of the source code. We propose GEML, a novel detection approach based on evolutionary machine learning using software properties of diverse nature. Firstly, GEML makes use of an evolutionary algorithm to extract those characteristics that better describe the DP, formulated in terms of human-readable rules, whose syntax is conformant with a context-free grammar. Secondly, a rule-based classifier is built to predict whether new code contains a hidden DP implementation. GEML has been validated over five DPs taken from a public repository recurrently adopted by machine learning studies. Then, we increase this number up to 15 diverse DPs, showing its effectiveness and robustness in terms of detection capability. An initial parameter study served to tune a parameter setup whose performance guarantees the general applicability of this approach without the need to adjust complex parameters to a specific pattern. Finally, a demonstration tool is also provided.

Neural solvers based on attention mechanism have demonstrated remarkable effectiveness in solving vehicle routing problems. However, in the generalization process from small scale to large scale, we find a phenomenon of the dispersion of attention scores in existing neural solvers, which leads to poor performance. To address this issue, this paper proposes a distance-aware attention reshaping method, assisting neural solvers in solving large-scale vehicle routing problems. Specifically, without the need for additional training, we utilize the Euclidean distance information between current nodes to adjust attention scores. This enables a neural solver trained on small-scale instances to make rational choices when solving a large-scale problem. Experimental results show that the proposed method significantly outperforms existing state-of-the-art neural solvers on the large-scale CVRPLib dataset.

Large datasets often contain multiple distinct feature sets, or views, that offer complementary information that can be exploited by multi-view learning methods to improve results. We investigate anatomical multi-view data, where each brain anatomical structure is described with multiple feature sets. In particular, we focus on sets of white matter microstructure and connectivity features from diffusion MRI, as well as sets of gray matter area and thickness features from structural MRI. We investigate machine learning methodology that applies multi-view approaches to improve the prediction of non-imaging phenotypes, including demographics (age), motor (strength), and cognition (picture vocabulary). We present an explainable multi-view network (EMV-Net) that can use different anatomical views to improve prediction performance. In this network, each individual anatomical view is processed by a view-specific feature extractor and the extracted information from each view is fused using a learnable weight. This is followed by a wavelet transform-based module to obtain complementary information across views which is then applied to calibrate the view-specific information. Additionally, the calibrator produces an attention-based calibration score to indicate anatomical structures' importance for interpretation.

Ministers need to "immediately" update the law to acknowledge that computers are fallible or risk a repeat of the Horizon scandal, legal experts say. In English and Welsh law, computers are assumed to be "reliable" unless proven otherwise. But critics of this approach say this reverses the burden of proof normally applied in criminal cases. Stephen Mason, a barrister and expert on electronic evidence, said: "It says, for the person who's saying'there's something wrong with this computer', that they have to prove it. Even if it's the person accusing them who has the information."

Neuro-symbolic programs -- programs containing both machine learning components and traditional symbolic code -- are becoming increasingly widespread. However, we believe that there is still a lack of a general methodology for verifying these programs whose correctness depends on the behaviour of the machine learning components. In this paper, we identify the ``embedding gap'' -- the lack of techniques for linking semantically-meaningful ``problem-space'' properties to equivalent ``embedding-space'' properties -- as one of the key issues, and describe Vehicle, a tool designed to facilitate the end-to-end verification of neural-symbolic programs in a modular fashion. Vehicle provides a convenient language for specifying ``problem-space'' properties of neural networks and declaring their relationship to the ``embedding-space", and a powerful compiler that automates interpretation of these properties in the language of a chosen machine-learning training environment, neural network verifier, and interactive theorem prover. We demonstrate Vehicle's utility by using it to formally verify the safety of a simple autonomous car equipped with a neural network controller.