Zobrazeno 1 - 10
of 559
pro vyhledávání: '"Li, Xiaocheng"'
Predicting simple function classes has been widely used as a testbed for developing theory and understanding of the trained Transformer's in-context learning (ICL) ability. In this paper, we revisit the training of Transformers on linear regression t
Externí odkaz:
http://arxiv.org/abs/2405.15115
Autor:
Wang, Hanzhao, Pan, Yu, Sun, Fupeng, Liu, Shang, Talluri, Kalyan, Chen, Guanting, Li, Xiaocheng
In this paper, we consider the supervised pretrained transformer for a class of sequential decision-making problems. The class of considered problems is a subset of the general formulation of reinforcement learning in that there is no transition prob
Externí odkaz:
http://arxiv.org/abs/2405.14219
In this paper, we study the problem of uncertainty estimation and calibration for LLMs. We first formulate the uncertainty estimation problem for LLMs and then propose a supervised approach that takes advantage of the labeled datasets and estimates t
Externí odkaz:
http://arxiv.org/abs/2404.15993
In this paper, we study the problem of watermarking large language models (LLMs). We consider the trade-off between model distortion and detection ability and formulate it as a constrained optimization problem based on the green-red algorithm of Kirc
Externí odkaz:
http://arxiv.org/abs/2403.13027
Discrete-choice models, such as Multinomial Logit, Probit, or Mixed-Logit, are widely used in Marketing, Economics, and Operations Research: given a set of alternatives, the customer is modeled as choosing one of the alternatives to maximize a (laten
Externí odkaz:
http://arxiv.org/abs/2310.08716
Electrifying heavy-duty trucks offers a substantial opportunity to curtail carbon emissions, advancing toward a carbon-neutral future. However, the inherent challenges of limited battery energy and the sheer weight of heavy-duty trucks lead to reduce
Externí odkaz:
http://arxiv.org/abs/2310.04440
As artificial intelligence (AI) systems play an increasingly prominent role in human decision-making, challenges surface in the realm of human-AI interactions. One challenge arises from the suboptimal AI policies due to the inadequate consideration o
Externí odkaz:
http://arxiv.org/abs/2310.00817
Discrete-choice models are used in economics, marketing and revenue management to predict customer purchase probabilities, say as a function of prices and other features of the offered assortment. While they have been shown to be expressive, capturin
Externí odkaz:
http://arxiv.org/abs/2308.05617
Learning with rejection has been a prototypical model for studying the human-AI interaction on prediction tasks. Upon the arrival of a sample instance, the model first uses a rejector to decide whether to accept and use the AI predictor to make a pre
Externí odkaz:
http://arxiv.org/abs/2307.02932
Autor:
Liu, Shang, Li, Xiaocheng
Uncertainty sampling is a prevalent active learning algorithm that queries sequentially the annotations of data samples which the current prediction model is uncertain about. However, the usage of uncertainty sampling has been largely heuristic: (i)
Externí odkaz:
http://arxiv.org/abs/2307.02719