stp2y

arXiv:2405.15877v1 Announce Type: new Abstract: Large language models (LLMs) significantly enhance the performance of various applications, but they are computationally intensive and energy-demanding. This makes it challenging to deploy them on devices with limited resources, such as personal computers and mobile/wearable devices, and results in substantial inference costs in resource-rich environments like cloud servers. To extend the use of LLMs, we introduce a low-rank decomposition approach to effectively compress these models, tailored to the requirements of specific applications. We observe that LLMs pretrained on general datasets contain many redundant components not needed for particular applications. Our method focuses on identifying…

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Source link lol

arXiv:2405.15964v1 Announce Type: new Abstract: The effect of syntactic priming exhibits three well-documented empirical properties: the lexical boost, the inverse frequency effect, and the asymmetrical decay. We aim to show how these three empirical phenomena can be reconciled in a general learning framework, the hierarchical Bayesian model (HBM). The model represents syntactic knowledge in a hierarchical structure of syntactic statistics, where a lower level represents the verb-specific biases of syntactic decisions, and a higher level represents the abstract bias as an aggregation of verb-specific biases. This knowledge is updated in response to experience by Bayesian inference. In simulations, we show…

(Tee11/Shutterstock) Getting access to consistent, high-quality data ranks as one of the toughest challenges in big data, advanced analytics, and AI. It’s a challenge that is being taken up by Fusion by J.P. Morgan with its new Containerized Data offering, which provides institutional investors with consistent, enriched data that’s been standardized with a common semantic layer. The worst-kept secret in big data is that data prep consumes the vast majority of time in analytics, machine learning, and AI projects. Raw data does contain signals that data scientists so desperately want to leverage for competitive gain, but that data must be…