Our study explores how well the state-of-the-art Large Language Models (LLMs), like GPT-4 and Mistral, can assess the quality of scientific summaries or, more fittingly, scientific syntheses, comparing their evaluations to those of human annotators. We used a dataset of 100 research questions and their syntheses made by GPT-4 from abstracts of five related papers, checked against human quality ratings. The study evaluates both the closed-source GPT-4 and the open-source Mistral model's ability to rate these summaries and provide reasons for their judgments. Preliminary results show that LLMs can offer logical explanations that somewhat match the quality ratings, yet a deeper statistical analysis shows a weak correlation between LLM and human ratings, suggesting the potential and current limitations of LLMs in scientific synthesis evaluation.

Their vast number of trainable parameters necessitates a wealth of data to achieve accuracy and mitigate overfitting. However, experimental measurements are often limited and costly to obtain in sufficient quantities for finetuning. To this end, we present a physics-based training pipeline that tackles the pathology of data scarcity. The core enabler is a physics-based modeling framework that generates a multitude of synthetic data to align the LLM to a physically consistent initial state before finetuning. Our framework features a two-phase training strategy: (1) utilizing the large-in-amount while less accurate synthetic data for supervised pretraining, and (2) finetuning the phase-1 model with limited experimental data. We empirically demonstrate that supervised pretraining is vital to obtaining accurate finetuned LLMs, via the lens of learning polymer flammability metrics where cone calorimeter data is sparse.

Hierarchical time-series forecasting (HTSF) is an important problem for many real-world business applications where the goal is to simultaneously forecast multiple time-series that are related to each other via a hierarchical relation. Recent works, however, do not address two important challenges that are typically observed in many demand forecasting applications at large companies. First, many time-series at lower levels of the hierarchy have high sparsity i.e., they have a significant number of zeros. Most HTSF methods do not address this varying sparsity across the hierarchy. Further, they do not scale well to the large size of the real-world hierarchy typically unseen in benchmarks used in literature. We resolve both these challenges by proposing HAILS, a novel probabilistic hierarchical model that enables accurate and calibrated probabilistic forecasts across the hierarchy by adaptively modeling sparse and dense time-series with different distributional assumptions and reconciling them to adhere to hierarchical constraints. We show the scalability and effectiveness of our methods by evaluating them against real-world demand forecasting datasets. We deploy HAILS at a large chemical manufacturing company for a product demand forecasting application with over ten thousand products and observe a significant 8.5\% improvement in forecast accuracy and 23% better improvement for sparse time-series. The enhanced accuracy and scalability make HAILS a valuable tool for improved business planning and customer experience.

In this paper, we demonstrate a surprising capability of large language models (LLMs): given only input feature names and a description of a prediction task, they are capable of selecting the most predictive features, with performance rivaling the standard tools of data science. Remarkably, these models exhibit this capacity across various query mechanisms. For example, we zero-shot prompt an LLM to output a numerical importance score for a feature (e.g., "blood pressure") in predicting an outcome of interest (e.g., "heart failure"), with no additional context. In particular, we find that the latest models, such as GPT-4, can consistently identify the most predictive features regardless of the query mechanism and across various prompting strategies. We illustrate these findings through extensive experiments on real-world data, where we show that LLM-based feature selection consistently achieves strong performance competitive with data-driven methods such as the LASSO, despite never having looked at the downstream training data. Our findings suggest that LLMs may be useful not only for selecting the best features for training but also for deciding which features to collect in the first place. This could potentially benefit practitioners in domains like healthcare, where collecting high-quality data comes at a high cost.

In recent years, pretraining models have made significant advancements in the fields of natural language processing (NLP), computer vision (CV), and life sciences. The significant advancements in NLP and CV are predominantly driven by the expansion of model parameters and data size, a phenomenon now recognized as the scaling laws. However, research exploring scaling law in molecular pretraining models remains unexplored. In this work, we present Uni-Mol2 , an innovative molecular pretraining model that leverages a two-track transformer to effectively integrate features at the atomic level, graph level, and geometry structure level. Along with this, we systematically investigate the scaling law within molecular pretraining models, characterizing the power-law correlations between validation loss and model size, dataset size, and computational resources. Consequently, we successfully scale Uni-Mol2 to 1.1 billion parameters through pretraining on 800 million conformations, making it the largest molecular pretraining model to date. Extensive experiments show consistent improvement in the downstream tasks as the model size grows. The Uni-Mol2 with 1.1B parameters also outperforms existing methods, achieving an average 27% improvement on the QM9 and 14% on COMPAS-1D dataset.

Large Language Models (LLMs) have emerged as a potential solution to assist digital health development with patient education, commonly medication-related enquires. We trained and validated Med-Pal, a medication domain-specific LLM-chatbot fine-tuned with a fine-grained and expert curated dataset from a selection of five light-weighted open-source LLMs of smaller parameter size (7 billion or less) regarding computational constraints and prioritizing operational efficiency. A multi-disciplinary team performed a clinical evaluation of LLMs responses using the SCORE criteria, focusing on safety, accuracy, bias, reproducibility, and ease of understanding. Best performing light-weighted LLM was chosen as Med-Pal for further engineering with guard-railing using adversarial prompting. Med-Pal and existing light-weighted LLMs, including pretrained Biomistral and finetuned Meerkat, were validated on an independent dataset on a broad range of medication-related questions (231 in total), 12 different question types across 14 different medication classes. Mistral-7b emerged as the top performer among selected lightweight LLMs, achieving the highest median score of 14 and 71.9% high-quality responses in accuracy and safety domains, hence chosen as the backbone LLM for Med-Pal. When compared against Biomistral, Med-pal outperformed in generating responses appropriate for patient communication, with significant reductions bias and errors typical of general LLMs. Comparable performance was observed when comparing Med-Pal with Meerkat. Med-Pal showcases the feasibility of developing and employing fine-tuned light-weighted LLMs to enhance digital health communications.

Rare events are occurrences that take place with a significantly lower frequency than more common regular events. In manufacturing, predicting such events is particularly important, as they lead to unplanned downtime, shortening equipment lifespan, and high energy consumption. The occurrence of events is considered frequently-rare if observed in more than 10% of all instances, very-rare if it is 1-5%, moderately-rare if it is 5-10%, and extremely-rare if less than 1%. The rarity of events is inversely correlated with the maturity of a manufacturing industry. Typically, the rarity of events affects the multivariate data generated within a manufacturing process to be highly imbalanced, which leads to bias in predictive models. This paper evaluates the role of data enrichment techniques combined with supervised machine-learning techniques for rare event detection and prediction. To address the data scarcity, we use time series data augmentation and sampling methods to amplify the dataset with more multivariate features and data points while preserving the underlying time series patterns in the combined alterations. Imputation techniques are used in handling null values in datasets. Considering 15 learning models ranging from statistical learning to machine learning to deep learning methods, the best-performing model for the selected datasets is obtained and the efficacy of data enrichment is evaluated. Based on this evaluation, our results find that the enrichment procedure enhances up to 48% of F1 measure in rare failure event detection and prediction of supervised prediction models. We also conduct empirical and ablation experiments on the datasets to derive dataset-specific novel insights. Finally, we investigate the interpretability aspect of models for rare event prediction, considering multiple methods.

The dispatch optimization of coal mine integrated energy system is challenging due to high dimensionality, strong coupling constraints, and multiobjective. Existing constrained multiobjective evolutionary algorithms struggle with locating multiple small and irregular feasible regions, making them inaplicable to this problem. To address this issue, we here develop a multitask evolutionary algorithm framework that incorporates the dispatch correlated domain knowledge to effectively deal with strong constraints and multiobjective optimization. Possible evolutionary multitask construction strategy based on complex constraint relationship analysis and handling, i.e., constraint coupled spatial decomposition, constraint strength classification and constraint handling technique, is first explored. Within the multitask evolutionary optimization framework, two strategies, i.e., an elite guided knowledge transfer by designing a special crowding distance mechanism to select dominant individuals from each task, and an adaptive neighborhood technology based mutation to effectively balance the diversity and convergence of each optimized task for the differential evolution algorithm, are further developed. The performance of the proposed algorithm in feasibility, convergence, and diversity is demonstrated in a case study of a coal mine integrated energy system by comparing with CPLEX solver and seven constrained multiobjective evolutionary algorithms.

Poor bucking decisions made by forest harvesters can have a negative effect on the products that are generated from the logs. Making the right bucking decisions is not an easy task because harvesters must rely on predictions of the stem profile for the part of the stems that is not yet measured. The goal of this project is to improve the bucking decisions made by forest harvesters with a stochastic bucking method. We developed a Long Short-Term Memory (LSTM) neural network that predicted the parameters of a Gaussian distribution conditioned on the known part of the stem, enabling the creation of multiple samples of stem profile predictions for the unknown part of the stem. The bucking decisions could then be optimized using a novel stochastic bucking algorithm which used all the stem profiles generated to choose the logs to generate from the stem. The stochastic bucking algorithm was compared to two benchmark models: A polynomial model that could not condition its predictions on more than one diameter measurement, and a deterministic LSTM neural network. All models were evaluated on stem profiles of four coniferous species prevalent in eastern Canada. In general, the best bucking decisions were taken by the stochastic LSTM models, demonstrating the usefulness of the method. The second-best results were mostly obtained by the deterministic LSTM model and the worst results by the polynomial model, corroborating the usefulness of conditioning the stem curve predictions on multiple measurements.

As AI companies work furiously to improve the intelligence and usefulness of their products, their demand for cheap, plentiful energy has skyrocketed. This gold rush has been extremely profitable for an unlikely beneficiary: Bitcoin miners. In recent months, major Bitcoin mining companies have started to swap out some of their mining equipment in favor of rigs used to run and train AI systems. These companies believe that AI training could provide a safer and more consistent source of revenue than the volatile crypto industry. And so far, these pivots have been warmly received by investors, leading to the market cap of 14 major bitcoin mining companies jumping in value by 22%, or 4 billion, since the beginning of June, J.P. Morgan reported on June 24. This transition reflects several trends of the moment: the roaring hype cycle of AI; the dwindling access to power, and a tenuous bitcoin mining landscape following the bitcoin halving.