Stroke is a major global health problem that causes mortality and morbidity. Predicting the outcomes of stroke intervention can facilitate clinical decision-making and improve patient care. Engaging and developing deep learning techniques can help to analyse large and diverse medical data, including brain scans, medical reports and other sensor information, such as EEG, ECG, EMG and so on. Despite the common data standardisation challenge within medical image analysis domain, the future of deep learning in stroke outcome prediction lie in using multimodal information, including final infarct data, to achieve better prediction of long-term functional outcomes. This article provides a broad review of recent advances and applications of deep learning in the prediction of stroke outcomes, including (i) the data and models used, (ii) the prediction tasks and measures of success, (iii) the current challenges and limitations, and (iv) future directions and potential benefits. This comprehensive review aims to provide researchers, clinicians, and policy makers with an up-to-date understanding of this rapidly evolving and promising field.
In recent years, explainable methods for artificial intelligence (XAI) have tried to reveal and describe models' decision mechanisms in the case of classification tasks. However, XAI for semantic segmentation and in particular for single instances has been little studied to date. Understanding the process underlying automatic segmentation of single instances is crucial to reveal what information was used to detect and segment a given object of interest. In this study, we proposed two instance-level explanation maps for semantic segmentation based on SmoothGrad and Grad-CAM++ methods. Then, we investigated their relevance for the detection and segmentation of white matter lesions (WML), a magnetic resonance imaging (MRI) biomarker in multiple sclerosis (MS). 687 patients diagnosed with MS for a total of 4043 FLAIR and MPRAGE MRI scans were collected at the University Hospital of Basel, Switzerland. Data were randomly split into training, validation and test sets to train a 3D U-Net for MS lesion segmentation. We observed 3050 true positive (TP), 1818 false positive (FP), and 789 false negative (FN) cases. We generated instance-level explanation maps for semantic segmentation, by developing two XAI methods based on SmoothGrad and Grad-CAM++. We investigated: 1) the distribution of gradients in saliency maps with respect to both input MRI sequences; 2) the model's response in the case of synthetic lesions; 3) the amount of perilesional tissue needed by the model to segment a lesion. Saliency maps (based on SmoothGrad) in FLAIR showed positive values inside a lesion and negative in its neighborhood. Peak values of saliency maps generated for these four groups of volumes presented distributions that differ significantly from one another, suggesting a quantitative nature of the proposed saliency. Contextual information of 7mm around the lesion border was required for their segmentation.
Large language models (LLMs) have empowered intelligent agents to execute intricate tasks within domain-specific software such as browsers and games. However, when applied to general-purpose software systems like operating systems, LLM agents face three primary challenges. Firstly, the action space is vast and dynamic, posing difficulties for LLM agents to maintain an up-to-date understanding and deliver accurate responses. Secondly, real-world tasks often require inter-application cooperation}, demanding farsighted planning from LLM agents. Thirdly, agents need to identify optimal solutions aligning with user constraints, such as security concerns and preferences. These challenges motivate AndroidArena, an environment and benchmark designed to evaluate LLM agents on a modern operating system. To address high-cost of manpower, we design a scalable and semi-automated method to construct the benchmark. In the task evaluation, AndroidArena incorporates accurate and adaptive metrics to address the issue of non-unique solutions. Our findings reveal that even state-of-the-art LLM agents struggle in cross-APP scenarios and adhering to specific constraints. Additionally, we identify a lack of four key capabilities, i.e., understanding, reasoning, exploration, and reflection, as primary reasons for the failure of LLM agents. Furthermore, we provide empirical analysis on the failure of reflection, and improve the success rate by 27% with our proposed exploration strategy. This work is the first to present valuable insights in understanding fine-grained weakness of LLM agents, and offers a path forward for future research in this area. Environment, benchmark, and evaluation code for AndroidArena are released at https://github.com/AndroidArenaAgent/AndroidArena.
While large language models (LLMs) are increasingly being used for program synthesis, they lack the global view needed to develop useful abstractions; they generally predict programs one at a time, often repeating the same functionality. Generating redundant code from scratch is both inefficient and error-prone. To address this, we propose Refactoring for Generalizable Abstraction Learning (ReGAL), a gradient-free method for learning a library of reusable functions via code refactorization, i.e., restructuring code without changing its execution output. ReGAL learns from a small set of existing programs, iteratively verifying and refining its abstractions via execution. We find that the shared function libraries discovered by ReGAL make programs easier to predict across diverse domains. On five datasets -- LOGO graphics generation, Date reasoning, TextCraft (a Minecraft-based text-game) MATH, and TabMWP -- both open-source and proprietary LLMs improve in accuracy when predicting programs with ReGAL functions. For CodeLlama-13B, ReGAL results in absolute accuracy increases of 11.5% on LOGO, 26.1% on date understanding, and 8.1% on TextCraft, outperforming GPT-3.5 in two of three domains. Our analysis reveals ReGAL's abstractions encapsulate frequently-used subroutines as well as environment dynamics.
Language models are achieving impressive performance on various tasks by aggressively adopting inference-time prompting techniques, such as zero-shot and few-shot prompting. In this work, we introduce EchoPrompt, a simple yet effective approach that prompts the model to rephrase its queries before answering them. EchoPrompt is adapted for both zero-shot and few-shot in-context learning with standard and chain-of-thought prompting. Experimental results show that EchoPrompt yields substantial improvements across all these settings for four families of causal language models. These improvements are observed across various numerical reasoning (e.g. GSM8K, SVAMP), reading comprehension (e.g. DROP), and logical reasoning (e.g. Coin Flipping) tasks. On average, EchoPrompt improves the Zero-shot-CoT performance of code-davinci-002 by 5% in numerical tasks and 13% in reading comprehension tasks. We investigate the factors contributing to EchoPrompt's effectiveness through ablation studies, which reveal that both the original query and the model-generated rephrased version are instrumental in its performance gains. Our empirical results indicate that EchoPrompt is an effective technique that enhances in-context learning performance. We recommend incorporating EchoPrompt into various baseline prompting strategies to achieve performance boosts.
Semantic segmentation (classification) of Earth Observation imagery is a crucial task in remote sensing. This paper presents a comprehensive review of technical factors to consider when designing neural networks for this purpose. The review focuses on Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Generative Adversarial Networks (GANs), and transformer models, discussing prominent design patterns for these ANN families and their implications for semantic segmentation. Common pre-processing techniques for ensuring optimal data preparation are also covered. These include methods for image normalization and chipping, as well as strategies for addressing data imbalance in training samples, and techniques for overcoming limited data, including augmentation techniques, transfer learning, and domain adaptation. By encompassing both the technical aspects of neural network design and the data-related considerations, this review provides researchers and practitioners with a comprehensive and up-to-date understanding of the factors involved in designing effective neural networks for semantic segmentation of Earth Observation imagery.
Temporal and numerical expression understanding is of great importance in many downstream Natural Language Processing (NLP) and Information Retrieval (IR) tasks. However, much previous work covers only a few sub-types and focuses only on entity extraction, which severely limits the usability of identified mentions. In order for such entities to be useful in downstream scenarios, coverage and granularity of sub-types are important; and, even more so, providing resolution into concrete values that can be manipulated. Furthermore, most previous work addresses only a handful of languages. Here we describe a multi-lingual evaluation dataset - NTX - covering diverse temporal and numerical expressions across 14 languages and covering extraction, normalization, and resolution. Along with the dataset we provide a robust rule-based system as a strong baseline for comparisons against other models to be evaluated in this dataset. Data and code are available at \url{https://aka.ms/NTX}.
The use of NLP in the realm of financial technology is broad and complex, with applications ranging from sentiment analysis and named entity recognition to question answering. Large Language Models (LLMs) have been shown to be effective on a variety of tasks; however, no LLM specialized for the financial domain has been reported in literature. In this work, we present BloombergGPT, a 50 billion parameter language model that is trained on a wide range of financial data. We construct a 363 billion token dataset based on Bloomberg's extensive data sources, perhaps the largest domain-specific dataset yet, augmented with 345 billion tokens from general purpose datasets. We validate BloombergGPT on standard LLM benchmarks, open financial benchmarks, and a suite of internal benchmarks that most accurately reflect our intended usage. Our mixed dataset training leads to a model that outperforms existing models on financial tasks by significant margins without sacrificing performance on general LLM benchmarks. Additionally, we explain our modeling choices, training process, and evaluation methodology. We release Training Chronicles (Appendix C) detailing our experience in training BloombergGPT.
We study the task of prompting large-scale language models to perform multi-step reasoning. Existing work shows that when prompted with a chain of thoughts (CoT), sequences of short sentences describing intermediate reasoning steps towards a final answer, large language models can generate new reasoning chains and predict answers for new inputs. A central question is which reasoning examples make the most effective prompts. In this work, we propose complexity-based prompting, a simple and effective example selection scheme for multi-step reasoning. We show that prompts with higher reasoning complexity, i.e., chains with more reasoning steps, achieve substantially better performance on multi-step reasoning tasks over strong baselines. We further extend our complexity-based criteria from prompting (selecting inputs) to decoding (selecting outputs), where we sample multiple reasoning chains from the model, then choose the majority of generated answers from complex reasoning chains (over simple chains). When used to prompt GPT-3 and Codex, our approach substantially improves multi-step reasoning accuracy and achieves new state-of-the-art (SOTA) performance on three math benchmarks (GSM8K, MultiArith, and MathQA) and two BigBenchHard tasks (Date Understanding and Penguins), with an average +5.3 and up to +18 accuracy improvements. Compared with existing example selection schemes like manual tuning or retrieval-based selection, selection based on reasoning complexity is intuitive, easy to implement, and annotation-efficient. Further results demonstrate the robustness of performance gains from complex prompts under format perturbation and distribution shift.
Pretrained large language models (LLMs) are widely used in many sub-fields of natural language processing (NLP) and generally known as excellent few-shot learners with task-specific exemplars. Notably, chain of thought (CoT) prompting, a recent technique for eliciting complex multi-step reasoning through step-by-step answer examples, achieved the state-of-the-art performances in arithmetics and symbolic reasoning, difficult system-2 tasks that do not follow the standard scaling laws for LLMs. While these successes are often attributed to LLMs' ability for few-shot learning, we show that LLMs are decent zero-shot reasoners by simply adding "Let's think step by step" before each answer. Experimental results demonstrate that our Zero-shot-CoT, using the same single prompt template, significantly outperforms zero-shot LLM performances on diverse benchmark reasoning tasks including arithmetics (MultiArith, GSM8K, AQUA-RAT, SVAMP), symbolic reasoning (Last Letter, Coin Flip), and other logical reasoning tasks (Date Understanding, Tracking Shuffled Objects), without any hand-crafted few-shot examples, e.g. increasing the accuracy on MultiArith from 17.7% to 78.7% and GSM8K from 10.4% to 40.7% with large InstructGPT model (text-davinci-002), as well as similar magnitudes of improvements with another off-the-shelf large model, 540B parameter PaLM. The versatility of this single prompt across very diverse reasoning tasks hints at untapped and understudied fundamental zero-shot capabilities of LLMs, suggesting high-level, multi-task broad cognitive capabilities may be extracted by simple prompting. We hope our work not only serves as the minimal strongest zero-shot baseline for the challenging reasoning benchmarks, but also highlights the importance of carefully exploring and analyzing the enormous zero-shot knowledge hidden inside LLMs before crafting finetuning datasets or few-shot exemplars.
We investigate the optimal model size and number of tokens for training a transformer language model under a given compute budget. We find that current large language models are significantly undertrained, a consequence of the recent focus on scaling language models whilst keeping the amount of training data constant. By training over \nummodels language models ranging from 70 million to over 16 billion parameters on 5 to 500 billion tokens, we find that for compute-optimal training, the model size and the number of training tokens should be scaled equally: for every doubling of model size the number of training tokens should also be doubled. We test this hypothesis by training a predicted compute-optimal model, \chinchilla, that uses the same compute budget as \gopher but with 70B parameters and 4$\times$ more more data. \chinchilla uniformly and significantly outperforms \Gopher (280B), GPT-3 (175B), Jurassic-1 (178B), and Megatron-Turing NLG (530B) on a large range of downstream evaluation tasks. This also means that \chinchilla uses substantially less compute for fine-tuning and inference, greatly facilitating downstream usage. As a highlight, \chinchilla reaches a state-of-the-art average accuracy of 67.5\% on the MMLU benchmark, greater than a 7\% improvement over \gopher.
Language modelling provides a step towards intelligent communication systems by harnessing large repositories of written human knowledge to better predict and understand the world. In this paper, we present an analysis of Transformer-based language model performance across a wide range of model scales -- from models with tens of millions of parameters up to a 280 billion parameter model called Gopher. These models are evaluated on 152 diverse tasks, achieving state-of-the-art performance across the majority. Gains from scale are largest in areas such as reading comprehension, fact-checking, and the identification of toxic language, but logical and mathematical reasoning see less benefit. We provide a holistic analysis of the training dataset and model's behaviour, covering the intersection of model scale with bias and toxicity. Finally we discuss the application of language models to AI safety and the mitigation of downstream harms.