Large language models have been shown to achieve remarkable performance across a variety of natural language tasks using few-shot learning, which drastically reduces the number of task-specific training examples needed to adapt the model to a particular application. To further our understanding of the impact of scale on few-shot learning, we trained a 540-billion parameter, densely activated, Transformer language model, which we call Pathways Language Model (PaLM).We trained PaLM on 6144 TPU v4 chips using Pathways, a new ML system which enables highly efficient training across multiple TPU Pods. We demonstrate continued benefits of scaling by achieving state-ofthe-art few-shot learning results on hundreds of language understanding and generation benchmarks. On a number of these tasks, PaLM 540B achieves breakthrough performance, outperforming the finetuned stateof-the-art on a suite of multi-step reasoning tasks, and outperforming average human performance on the recently released BIG-bench benchmark. A significant number of BIG-bench tasks showed discontinuous improvements from model scale, meaning that performance steeply increased as we scaled to our largest model. PaLM also has strong capabilities in multilingual tasks and source code generation, which we demonstrate on a wide array of benchmarks. We additionally provide a comprehensive analysis on bias and toxicity, and study the extent of training data memorization with respect to model scale. Finally, we discuss the ethical considerations related to large language models and discuss potential mitigation strategies. * Equal Contribution. Author contributions and ordering details are listed in Appendix A.
SUMMARY Metabolites in the kynurenine pathway of tryptophan degradation are thought to play an important role in neurodegenerative disorders such as Alzheimer’s disease and Huntington’s disease. Metabolites that cause glutamate receptor-mediated excitotoxicity and free radical formation are elevated in the blood and vulnerable brain regions in these diseases, while levels of the neuroprotective metabolite kynurenic acid are often decreased. Here we describe the synthesis and characterization of JM6, a novel small-molecule pro-drug inhibitor of kynurenine 3-monooxygenase (KMO). JM6 raises kynurenic acid and reduces extracellular glutamate in the brain after chronic oral administration by inhibiting KMO in blood. In a transgenic mouse model of Alzheimer’s disease, JM6 prevented spatial memory deficits, anxiety-related behavior, and synaptic loss. JM6 also extended life span, prevented synaptic loss, and decreased microglial activation in a mouse model of Huntington’s disease. These findings support a critical link between blood cells and neurodegeneration that is mediated by KMO and the kynurenine pathway.
We propose a conditional non-autoregressive neural sequence model based on iterative refinement. The proposed model is designed based on the principles of latent variable models and denoising autoencoders, and is generally applicable to any sequence generation task. We extensively evaluate the proposed model on machine translation (En↔De and En↔Ro) and image caption generation, and observe that it significantly speeds up decoding while maintaining the generation quality comparable to the autoregressive counterpart.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.