Xuezhi Wang

Maximum Likelihood Estimation for Single Linkage Hierarchical Clustering

2015 · arXiv (Cornell University)

We derive a statistical model for estimation of a dendrogram from single linkage hierarchical clustering (SLHC) that takes account of uncertainty through noise or corruption in the measurements of separation of data. Our focus is …

Improving Classifier Robustness through Active Generation of Pairwise Counterfactuals

2023 · arXiv (Cornell University)

Counterfactual Data Augmentation (CDA) is a commonly used technique for improving robustness in natural language classifiers. However, one fundamental challenge is how to discover meaningful counterfactuals and efficiently label them, with minimal human labeling cost. …

A Minimalist Prompt for Zero-Shot Policy Learning

2024 · arXiv (Cornell University)

Transformer-based methods have exhibited significant generalization ability when prompted with target-domain demonstrations or example solutions during inference. Although demonstrations, as a way of task specification, can capture rich information that may be hard to specify …

Self-Consistency Improves Chain of Thought Reasoning in Language Models

2022 · arXiv (Cornell University)

Chain-of-thought prompting combined with pre-trained large language models has achieved encouraging results on complex reasoning tasks. In this paper, we propose a new decoding strategy, self-consistency, to replace the naive greedy decoding used in chain-of-thought …

PaLM: Scaling Language Modeling with Pathways

2022 · arXiv (Cornell University)

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 …

Least-to-Most Prompting Enables Complex Reasoning in Large Language Models

2022 · arXiv (Cornell University)

Chain-of-thought prompting has demonstrated remarkable performance on various natural language reasoning tasks. However, it tends to perform poorly on tasks which requires solving problems harder than the exemplars shown in the prompts. To overcome this …

UL2: Unifying Language Learning Paradigms

2022 · arXiv (Cornell University)

Existing pre-trained models are generally geared towards a particular class of problems. To date, there seems to be still no consensus on what the right architecture and pre-training setup should be. This paper presents a …

Scaling Instruction-Finetuned Language Models

2022 · arXiv (Cornell University)

Finetuning language models on a collection of datasets phrased as instructions has been shown to improve model performance and generalization to unseen tasks. In this paper we explore instruction finetuning with a particular focus on …