Systematic reviews are vital for guiding practice, research, and policy, yet they are often slow and labour-intensive. Large language models (LLMs) could offer a way to speed up and automate systematic reviews, but their performance in such tasks has not been comprehensively evaluated against humans, and no study has tested GPT-4, the biggest LLM so far. This pre-registered study evaluates GPT-4's capability in title/abstract screening, full-text review, and data extraction across various literature types and languages using a 'human-out-of-the-loop' approach. Although GPT-4 had accuracy on par with human performance in most tasks, results were skewed by chance agreement and dataset imbalance. After adjusting for these, there was a moderate level of performance for data extraction, and - barring studies that used highly reliable prompts - screening performance levelled at none to moderate for different stages and languages. When screening full-text literature using highly reliable prompts, GPT-4's performance was 'almost perfect.' Penalising GPT-4 for missing key studies using highly reliable prompts improved its performance even more. Our findings indicate that, currently, substantial caution should be used if LLMs are being used to conduct systematic reviews, but suggest that, for certain systematic review tasks delivered under reliable prompts, LLMs can rival human performance.
相關內容
Can generative AI help us speed up the authoring of tools to help self-represented litigants? In this paper, we describe 3 approaches to automating the completion of court forms: a generative AI approach that uses GPT-3 to iteratively prompt the user to answer questions, a constrained template-driven approach that uses GPT-4-turbo to generate a draft of questions that are subject to human review, and a hybrid method. We use the open source Docassemble platform in all 3 experiments, together with a tool created at Suffolk University Law School called the Assembly Line Weaver. We conclude that the hybrid model of constrained automated drafting with human review is best suited to the task of authoring guided interviews.
The Segment Anything Model (SAM) has recently emerged as a significant breakthrough in foundation models, demonstrating remarkable zero-shot performance in object segmentation tasks. While SAM is designed for generalization, it exhibits limitations in handling specific medical imaging tasks that require fine-structure segmentation or precise boundaries. In this paper, we focus on the task of cardiac magnetic resonance imaging (cMRI) short-axis view segmentation using the SAM foundation model. We conduct a comprehensive investigation of the impact of different prompting strategies (including bounding boxes, positive points, negative points, and their combinations) on segmentation performance. We evaluate on two public datasets using the baseline model and models fine-tuned with varying amounts of annotated data, ranging from a limited number of volumes to a fully annotated dataset. Our findings indicate that prompting strategies significantly influence segmentation performance. Combining positive points with either bounding boxes or negative points shows substantial benefits, but little to no benefit when combined simultaneously. We further observe that fine-tuning SAM with a few annotated volumes improves segmentation performance when properly prompted. Specifically, fine-tuning with bounding boxes has a positive impact, while fine-tuning without bounding boxes leads to worse results compared to baseline.
Organising an AI challenge does not end with the final event. The long-lasting impact also needs to be organised. This chapter covers the various activities after the challenge is formally finished. The target audience of different post-challenge activities is identified. The various outputs of the challenge are listed with the means to collect them. The main part of the chapter is a template for a typical post-challenge paper, including possible graphs as well as advice on how to turn the challenge into a long-lasting benchmark.
We explore the power of the unbounded Fan-Out gate and the Global Tunable gates generated by Ising-type Hamiltonians in constructing constant-depth quantum circuits, with particular attention to quantum memory devices. We propose two types of constant-depth constructions for implementing Uniformly Controlled Gates. These gates include the Fan-In gates defined by $|x\rangle|b\rangle\mapsto |x\rangle|b\oplus f(x)\rangle$ for $x\in\{0,1\}^n$ and $b\in\{0,1\}$, where $f$ is a Boolean function. The first of our constructions is based on computing the one-hot encoding of the control register $|x\rangle$, while the second is based on Boolean analysis and exploits different representations of $f$ such as its Fourier expansion. Via these constructions, we obtain constant-depth circuits for the quantum counterparts of read-only and read-write memory devices -- Quantum Random Access Memory (QRAM) and Quantum Random Access Gate (QRAG) -- of memory size $n$. The implementation based on one-hot encoding requires either $O(n\log{n}\log\log{n})$ ancillae and $O(n\log{n})$ Fan-Out gates or $O(n\log{n})$ ancillae and $6$ Global Tunable gates. On the other hand, the implementation based on Boolean analysis requires only $2$ Global Tunable gates at the expense of $O(n^2)$ ancillae.
Traffic accidents frequently lead to fatal injuries, contributing to over 50 million deaths until 2023. To mitigate driving hazards and ensure personal safety, it is crucial to assist vehicles in anticipating important objects during travel. Previous research on important object detection primarily assessed the importance of individual participants, treating them as independent entities and frequently overlooking the connections between these participants. Unfortunately, this approach has proven less effective in detecting important objects in complex scenarios. In response, we introduce Driving scene Relationship self-Understanding transformer (DRUformer), designed to enhance the important object detection task. The DRUformer is a transformer-based multi-modal important object detection model that takes into account the relationships between all the participants in the driving scenario. Recognizing that driving intention also significantly affects the detection of important objects during driving, we have incorporated a module for embedding driving intention. To assess the performance of our approach, we conducted a comparative experiment on the DRAMA dataset, pitting our model against other state-of-the-art (SOTA) models. The results demonstrated a noteworthy 16.2\% improvement in mIoU and a substantial 12.3\% boost in ACC compared to SOTA methods. Furthermore, we conducted a qualitative analysis of our model's ability to detect important objects across different road scenarios and classes, highlighting its effectiveness in diverse contexts. Finally, we conducted various ablation studies to assess the efficiency of the proposed modules in our DRUformer model.
Agent-based modeling has been around for decades, and applied widely across the social and natural sciences. The scope of this research method is now poised to grow dramatically as it absorbs the new affordances provided by Large Language Models (LLM)s. Generative Agent-Based Models (GABM) are not just classic Agent-Based Models (ABM)s where the agents talk to one another. Rather, GABMs are constructed using an LLM to apply common sense to situations, act "reasonably", recall common semantic knowledge, produce API calls to control digital technologies like apps, and communicate both within the simulation and to researchers viewing it from the outside. Here we present Concordia, a library to facilitate constructing and working with GABMs. Concordia makes it easy to construct language-mediated simulations of physically- or digitally-grounded environments. Concordia agents produce their behavior using a flexible component system which mediates between two fundamental operations: LLM calls and associative memory retrieval. A special agent called the Game Master (GM), which was inspired by tabletop role-playing games, is responsible for simulating the environment where the agents interact. Agents take actions by describing what they want to do in natural language. The GM then translates their actions into appropriate implementations. In a simulated physical world, the GM checks the physical plausibility of agent actions and describes their effects. In digital environments simulating technologies such as apps and services, the GM may handle API calls to integrate with external tools such as general AI assistants (e.g., Bard, ChatGPT), and digital apps (e.g., Calendar, Email, Search, etc.). Concordia was designed to support a wide array of applications both in scientific research and for evaluating performance of real digital services by simulating users and/or generating synthetic data.
Sample selection models represent a common methodology for correcting bias induced by data missing not at random. It is well known that these models are not empirically identifiable without exclusion restrictions. In other words, some variables predictive of missingness do not affect the outcome model of interest. The drive to establish this requirement often leads to the inclusion of irrelevant variables in the model. A recent proposal uses adaptive LASSO to circumvent this problem, but its performance depends on the so-called covariance assumption, which can be violated in small to moderate samples. Additionally, there are no tools yet for post-selection inference for this model. To address these challenges, we propose two families of spike-and-slab priors to conduct Bayesian variable selection in sample selection models. These prior structures allow for constructing a Gibbs sampler with tractable conditionals, which is scalable to the dimensions of practical interest. We illustrate the performance of the proposed methodology through a simulation study and present a comparison against adaptive LASSO and stepwise selection. We also provide two applications using publicly available real data. An implementation and code to reproduce the results in this paper can be found at //github.com/adam-iqbal/selection-spike-slab
To address the major issues associated with using Time-Use Survey (TUS) for simulating residential load curves, we present the SMACH approach, which combines qualitative and quantitative data with agent-based simulation. Our model consists of autonomous agents assigned with daily tasks. The agents try to accomplish their assigned tasks to the best of their abilities. Quantitative data are used to generate tasks assignments. Qualitative studies allow us to define how agents select, based on plausible cognitive principles, the tasks to accomplish depending on the context. Our results show a better representation of weekdays and weekends, a more flexible association of tasks with appliances, and an improved simulation of load curves compared to real data. Highlights $\bullet$ Discussion about Time-Use Surveys (TUS) limits and the use of TUS in activity and energy simulation $\bullet$ Presentation of complementary data both qualitative and quantitative used to complement TUS data $\bullet$ Proposition of an agent-based approach that balances these limitations
Forecast combination involves using multiple forecasts to create a single, more accurate prediction. Recently, feature-based forecasting has been employed to either select the most appropriate forecasting models or to optimize the weights of their combination. In this paper, we present a multi-task optimization paradigm that focuses on solving both problems simultaneously and enriches current operational research approaches to forecasting. In essence, it incorporates an additional learning and optimization task into the standard feature-based forecasting approach, focusing on the identification of an optimal set of forecasting methods. During the training phase, an optimization model with linear constraints and quadratic objective function is employed to identify accurate and diverse methods for each time series. Moreover, within the training phase, a neural network is used to learn the behavior of that optimization model. Once training is completed the candidate set of methods is identified using the network. The proposed approach elicits the essential role of diversity in feature-based forecasting and highlights the interplay between model combination and model selection when optimizing forecasting ensembles. Experimental results on a large set of series from the M4 competition dataset show that our proposal enhances point forecast accuracy compared to state-of-the-art methods.
Nowadays, the Convolutional Neural Networks (CNNs) have achieved impressive performance on many computer vision related tasks, such as object detection, image recognition, image retrieval, etc. These achievements benefit from the CNNs outstanding capability to learn the input features with deep layers of neuron structures and iterative training process. However, these learned features are hard to identify and interpret from a human vision perspective, causing a lack of understanding of the CNNs internal working mechanism. To improve the CNN interpretability, the CNN visualization is well utilized as a qualitative analysis method, which translates the internal features into visually perceptible patterns. And many CNN visualization works have been proposed in the literature to interpret the CNN in perspectives of network structure, operation, and semantic concept. In this paper, we expect to provide a comprehensive survey of several representative CNN visualization methods, including Activation Maximization, Network Inversion, Deconvolutional Neural Networks (DeconvNet), and Network Dissection based visualization. These methods are presented in terms of motivations, algorithms, and experiment results. Based on these visualization methods, we also discuss their practical applications to demonstrate the significance of the CNN interpretability in areas of network design, optimization, security enhancement, etc.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191