LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language

arXiv:2405.12856v1 Announce Type: cross
Abstract: Machine learning practitioners often face significant challenges in formally integrating their prior knowledge and beliefs into predictive models, limiting the potential for nuanced and context-aware analyses. Moreover, the expertise needed to integrate this prior knowledge into probabilistic modeling typically limits the application of these models to specialists. Our goal is to build a regression model that can process numerical data and make probabilistic predictions at arbitrary locations, guided by natural language text which describes a …

abstract application arxiv challenges context cs.cl cs.lg expertise face knowledge language llm machine machine learning modeling natural natural language numerical potential predictive predictive models prior probabilistic modeling processes stat.ml type