Search

The integration of Artificial Intelligence (AI), especially Large Language Models (LLMs), into the clinical diagnosis process offers significant potential to improve the efficiency and accessibility of medical care. While LLMs have shown some promise in the medical domain, their application in clinical diagnosis remains underexplored, especially in real-world clinical practice, where highly sophisticated, patient-specific decisions need to be made. Current evaluations of LLMs in this field are often narrow in scope, focusing on specific diseases or specialties and employing simplified diagnostic tasks. To bridge this gap, we introduce CliBench, a novel benchmark developed from the MIMIC IV dataset, offering a comprehensive and realistic assessment of LLMs' capabilities in clinical diagnosis. This benchmark not only covers diagnoses from a diverse range of medical cases across various specialties but also incorporates tasks of clinical significance: treatment procedure identification, lab test ordering and medication prescriptions. Supported by structured output ontologies, CliBench enables a precise and multi-granular evaluation, offering an in-depth understanding of LLM's capability on diverse clinical tasks of desired granularity. We conduct a zero-shot evaluation of leading LLMs to assess their proficiency in clinical decision-making. Our preliminary results shed light on the potential and limitations of current LLMs in clinical settings, providing valuable insights for future advancements in LLM-powered healthcare., Comment: Project page: https://clibench.github.io

We study automated intrusion detection in an IT infrastructure, specifically the problem of identifying the start of an attack, the type of attack, and the sequence of actions an attacker takes, based on continuous measurements from the infrastructure. We apply statistical learning methods, including Hidden Markov Model (HMM), Long Short-Term Memory (LSTM), and Random Forest Classifier (RFC) to map sequences of observations to sequences of predicted attack actions. In contrast to most related research, we have abundant data to train the models and evaluate their predictive power. The data comes from traces we generate on an in-house testbed where we run attacks against an emulated IT infrastructure. Central to our work is a machine-learning pipeline that maps measurements from a high-dimensional observation space to a space of low dimensionality or to a small set of observation symbols. Investigating intrusions in offline as well as online scenarios, we find that both HMM and LSTM can be effective in predicting attack start time, attack type, and attack actions. If sufficient training data is available, LSTM achieves higher prediction accuracy than HMM. HMM, on the other hand, requires less computational resources and less training data for effective prediction. Also, we find that the methods we study benefit from data produced by traditional intrusion detection systems like SNORT., Comment: A shortened version of this paper will appear in the conference proceedings of NOMS 2024 (IEEE/IFIP Network Operations and Management Symposium)

We present one of the preliminary NLP works under the challenging setup of Learning from Label Proportions (LLP), where the data is provided in an aggregate form called bags and only the proportion of samples in each class as the ground truth. This setup is inline with the desired characteristics of training models under Privacy settings and Weakly supervision. By characterizing some irregularities of the most widely used baseline technique DLLP, we propose a novel formulation that is also robust. This is accompanied with a learnability result that provides a generalization bound under LLP. Combining this formulation with a self-supervised objective, our method achieves better results as compared to the baselines in almost 87% of the experimental configurations which include large scale models for both long and short range texts across multiple metrics., Comment: accepted as long paper in Findings of EMNLP 2023

Most of the existing Large Language Model (LLM) benchmarks on scientific problem reasoning focus on problems grounded in high-school subjects and are confined to elementary algebraic operations. To systematically examine the reasoning capabilities required for solving complex scientific problems, we introduce an expansive benchmark suite SciBench for LLMs. SciBench contains a carefully curated dataset featuring a range of collegiate-level scientific problems from mathematics, chemistry, and physics domains. Based on the dataset, we conduct an in-depth benchmarking study of representative open-source and proprietary LLMs with various prompting strategies. The results reveal that the current LLMs fall short of delivering satisfactory performance, with the best overall score of merely 43.22%. Furthermore, through a detailed user study, we categorize the errors made by LLMs into ten problem-solving abilities. Our analysis indicates that no single prompting strategy significantly outperforms the others and some strategies that demonstrate improvements in certain problem-solving skills could result in declines in other skills. We envision that SciBench will catalyze further developments in the reasoning abilities of LLMs, thereby ultimately contributing to scientific research and discovery., Comment: To appear at ICML 2024

Information extraction tasks such as event extraction require an in-depth understanding of the output structure and sub-task dependencies. They heavily rely on task-specific training data in the form of (passage, target structure) pairs to obtain reasonable performance. However, obtaining such data through human annotation is costly, leading to a pressing need for low-resource information extraction approaches that require minimal human labeling for real-world applications. Fine-tuning supervised models with synthesized training data would be a generalizable method, but the existing data generation methods either still rely on large-scale ground-truth data or cannot be applied to complicated IE tasks due to their poor performance. To address these challenges, we propose STAR, a data generation method that leverages Large Language Models (LLMs) to synthesize data instances given limited seed demonstrations, thereby boosting low-resource information extraction performance. Our approach involves generating target structures (Y) followed by generating passages (X), all accomplished with the aid of LLMs. We design fine-grained step-by-step instructions to obtain the initial data instances. We further reduce errors and improve data quality through self-reflection error identification and self-refinement with iterative revision. Our experiments show that the data generated by STAR significantly improve the performance of low-resource event extraction and relation extraction tasks, even surpassing the effectiveness of human-curated data. Human assessment of the data quality shows STAR-generated data exhibits higher passage quality and better align with the task definitions compared with the human-curated data., Comment: To appear at AAAI'24. More info is at https://derek.ma/STAR

Oxide heterostructures exhibit many intriguing properties. Here we provide design principles for inducing multiple topological states in (001) ($AM$O$_3$)$_1$/($AM'$O$_3$)$_1$ oxide superlattices. Aided by first-principles calculations and model analysis, we show that a (Sr$M$O3)$_1$/(Sr$M'$O$_3$)$_1$ superlattice ($M$ = Nb, Ta and $M'$ = Rh, Ir) is a strong topological insulator with $Z_2$ index (1;001). More remarkably, a (SrMoO3)$_1$/(SrIrO3)$_1$ superlattice exhibits multiple coexisting topological insulator (TI) and topological Dirac semi-metal (TDS) states. The TDS state has a pair of type-II Dirac points near the Fermi level and symmetry-protected Dirac node lines. The surface TDS Dirac cone is sandwiched by two surface TI Dirac cones in the energy-momentum space. The non-trivial topological properties arise from the band inversion between $d$ orbitals of two dissimilar transition metal atoms and a particular parity property of (001) superlattice geometry. Our work demonstrates how to induce nontrivial topological states in (001) perovskite oxide heterostructures by rational design., Comment: 29 pages, 6 figures and 1 table

Current AI/ML methods for data-driven engineering use models that are mostly trained offline. Such models can be expensive to build in terms of communication and computing cost, and they rely on data that is collected over extended periods of time. Further, they become out-of-date when changes in the system occur. To address these challenges, we investigate online learning techniques that automatically reduce the number of available data sources for model training. We present an online algorithm called Online Stable Feature Set Algorithm (OSFS), which selects a small feature set from a large number of available data sources after receiving a small number of measurements. The algorithm is initialized with a feature ranking algorithm, a feature set stability metric, and a search policy. We perform an extensive experimental evaluation of this algorithm using traces from an in-house testbed and from a data center in operation. We find that OSFS achieves a massive reduction in the size of the feature set by 1-3 orders of magnitude on all investigated datasets. Most importantly, we find that the accuracy of a predictor trained on a OSFS-produced feature set is somewhat better than when the predictor is trained on a feature set obtained through offline feature selection. OSFS is thus shown to be effective as an online feature selection algorithm and robust regarding the sample interval used for feature selection. We also find that, when concept drift in the data underlying the model occurs, its effect can be mitigated by recomputing the feature set and retraining the prediction model., Comment: arXiv admin note: substantial text overlap with arXiv:2010.14907