BayesJudge: Bayesian Kernel Language Modelling with Confidence Uncertainty in Legal Judgment Prediction

arXiv:2404.10481v1 Announce Type: new
Abstract: Predicting legal judgments with reliable confidence is paramount for responsible legal AI applications. While transformer-based deep neural networks (DNNs) like BERT have demonstrated promise in legal tasks, accurately assessing their prediction confidence remains crucial. We present a novel Bayesian approach called BayesJudge that harnesses the synergy between deep learning and deep Gaussian Processes to quantify uncertainty through Bayesian kernel Monte Carlo dropout. Our method leverages informative priors and flexible data modelling via kernels, surpassing existing …

abstract ai applications applications arxiv bayesian bert confidence cs.lg judgment kernel language language modelling legal legal ai modelling networks neural networks novel prediction responsible tasks transformer type uncertainty