BYR Achieve · 镜像论坛

在上一期热点文献推荐中，我们为您推荐了通信领域的最新发展前沿，包括高于100GHz无线通信感知与安全的挑战和解决方案、实现移动目标自动跟踪与无线通信的基于计算机视觉的智能超表面系统、用于双向相位调制的自偏置非互易磁超表面、用于室内太赫兹无线通信的分布式可重构智能表面。本期我们为您选取了4篇文献，介绍AI大型语言模型在医学与生物学领域的最新发展前沿，包括由Google科研人员提出的用于评估LLM模型在临床知识方面的MultiMed QA评估基准、利用结构化和非结构化记录基于语言模型进行临床预测、大型语言模型生成跨家族可预测功能的蛋白质序列、使用大型语言模型从初级序列直接推断全原子级蛋白质结构。文献一评估大型语言模型在临床知识方面的表现 Large language models encode clinical knowledge Singhal, Karan, etc. NATURE, 2023, 620(7972): 172-180 Large language models (LLMs) have demonstrated impressive capabilities, but the bar for clinical applications is high. Attempts to assess the clinical knowledge of models typically rely on automated evaluations based on limited benchmarks. Here, to address these limitations, we present MultiMedQA, a benchmark combining six existing medical question answering datasets spanning professional medicine, research and consumer queries and a new dataset of medical questions searched online, HealthSearchQA. We propose a human evaluation framework for model answers along multiple axes including factuality, comprehension, reasoning, possible harm and bias. In addition, we evaluate Pathways Language Model (PaLM, a 540-billion parameter LLM) and its instruction-tuned variant, Flan-PaLM on MultiMedQA. Using a combination of prompting strategies, Flan-PaLM achieves state-of-the-art accuracy on every MultiMedQA multiple-choice dataset (MedQA, MedMCQA, PubMedQA and Measuring Massive Multitask Language Understanding (MMLU) clinical topics), including 67.6% accuracy on MedQA (US Medical Licensing Exam-style questions), surpassing the prior state of the art by more than 17%. However, human evaluation reveals key gaps. To resolve this, we introduce instruction prompt tuning, a parameter-efficient approach for aligning LLMs to new domains using a few exemplars. The resulting model, Med-PaLM, performs encouragingly, but remains inferior to clinicians. We show that comprehension, knowledge recall and reasoning improve with model scale and instruction prompt tuning, suggesting the potential utility of LLMs in medicine. Our human evaluations reveal limitations of today's models, reinforcing the importance of both evaluation frameworks and method development in creating safe, helpful LLMs for clinical applications. 阅读原文：https://www.nature.com/articles/s41586-023-06291-2 文献二利用结构化和非结构化记录基于大型语言模型进行临床预测 Health system-scale language models are all-purpose prediction engines Jiang, Lavender Yao, etc. NATURE, 2023, 619(7969): 357-362 Physicians make critical time-constrained decisions every day. Clinical predictive models can help physicians and administrators make decisions by forecasting clinical and operational events. Existing structured data-based clinical predictive models have limited use in everyday practice owing to complexity in data processing, as well as model development and deployment. Here we show that unstructured clinical notes from the electronic health record can enable the training of clinical language models, which can be used as all-purpose clinical predictive engines with low-resistance development and deployment. Our approach leverages recent advances in natural language processing to train a large language model for medical language (NYUTron) and subsequently fine-tune it across a wide range of clinical and operational predictive tasks. We evaluated our approach within our health system for five such tasks: 30-day all-cause readmission prediction, in-hospital mortality prediction, comorbidity index prediction, length of stay prediction, and insurance denial prediction. We show that NYUTron has an area under the curve (AUC) of 78.7-94.9%, with an improvement of 5.36-14.7% in the AUC compared with traditional models. We additionally demonstrate the benefits of pretraining with clinical text, the potential for increasing generalizability to different sites through fine-tuning and the full deployment of our system in a prospective, single-arm trial. These results show the potential for using clinical language models in medicine to read alongside physicians and provide guidance at the point of care. 阅读原文：https://www.nature.com/articles/s41586-023-06160-y 文献三大型语言模型生成跨家族可预测功能的蛋白质序列 Large language models generate functional protein sequences across diverse families Madani, Ali, etc. NATURE BIOTECHNOLOGY, 2023, 41(8): 1099–1106 Deep-learning language models have shown promise in various biotechnological applications, including protein design and engineering. Here we describe ProGen, a language model that can generate protein sequences with a predictable function across large protein families, akin to generating grammatically and semantically correct natural language sentences on diverse topics. The model was trained on 280 million protein sequences from >19,000 families and is augmented with control tags specifying protein properties. ProGen can be further fine-tuned to curated sequences and tags to improve controllable generation performance of proteins from families with sufficient homologous samples. Artificial proteins fine-tuned to five distinct lysozyme families showed similar catalytic efficiencies as natural lysozymes, with sequence identity to natural proteins as low as 31.4%. ProGen is readily adapted to diverse protein families, as we demonstrate with chorismate mutase and malate dehydrogenase. 阅读原文：https://www.nature.com/articles/s41587-022-01618-2 文献四使用大型语言模型从初级序列直接推断全原子级蛋白质结构 Evolutionary-scale prediction of atomic-level protein structure with a language model Lin, Zeming, etc. SCIENCE, 2023, 379(6637): 1123–1130 Recent advances in machine learning have leveraged evolutionary information in multiple sequence alignments to predict protein structure. We demonstrate direct inference of full atomic-level protein structure from primary sequence using a large language model. As language models of protein sequences are scaled up to 15 billion parameters, an atomic-resolution picture of protein structure emerges in the learned representations. This results in an order-of-magnitude acceleration of high-resolution structure prediction, which enables large-scale structural characterization of metagenomic proteins. We apply this capability to construct the ESM Metagenomic Atlas by predicting structures for >617 million metagenomic protein sequences, including >225 million that are predicted with high confidence, which gives a view into the vast breadth and diversity of natural proteins. 阅读原文：https://www.science.org/doi/10.1126/science.ade2574 “前沿文献专题推荐服务”是图书馆情报服务部学科服务的重要内容。欢迎有相关需求的科研人员与我们联系，我们将为您提供更有针对性的定题服务。联系电话：62281933 62283502 地址：西土城校区图书馆125室情报服务部联系人：杨老师闫老师邮箱：yandong80@bupt.edu.cn

热点文献带您关注AI大型语言模型的最新进展——图书馆前沿文献