An official website of the United States government
Language model (LM) prompting—a popular paradigm for solving NLP tasks—has been shown to be susceptible to miscalibration and brittleness to slight prompt variations, caused by its discriminative prompting approach, i.e., predicting the label given the input. To address these issues, we propose Gen-Z—a generative prompting framework for zero-shot text classification. GEN-Z is generative, as it measures the LM likelihood of input text, conditioned on natural language descriptions of labels. The framework is multivariate, as label descriptions allow us to seamlessly integrate additional contextual information about the labels to improve task performance. On various standard classification benchmarks, with six open-source LM families, we show that zero-shot classification with simple contextualization of the data source of the evaluation set consistently outperforms both zero-shot and few-shot baselines while improving robustness to prompt variations. Further, our approach enables personalizing classification in a zero-shot manner by incorporating author, subject, or reader information in the label descriptions.
more »
« less
Incorporating Label Uncertainty in Understanding Adversarial Robustness.
A fundamental question in adversarial machine learning is whether a robust classifier exists for a given task. A line of research has made some progress towards this goal by studying the concentration of measure, but we argue standard concentration fails to fully characterize the intrinsic robustness of a classification problem since it ignores data labels which are essential to any classification task. Building on a novel definition of label uncertainty, we empirically demonstrate that error regions induced by state-of-the-art models tend to have much higher label uncertainty than randomly-selected subsets. This observation motivates us to adapt a concentration estimation algorithm to account for label uncertainty, resulting in more accurate intrinsic robustness measures for benchmark image classification problems.
more »
« less
- Award ID(s):
- 1804603
- PAR ID:
- 10333900
- Date Published:
- Journal Name:
- International Conference on Learning Representations (ICLR)
- Volume:
- 2022
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract We investigate how disagreement in natural language inference (NLI) annotation arises. We developed a taxonomy of disagreement sources with 10 categories spanning 3 high- level classes. We found that some disagreements are due to uncertainty in the sentence meaning, others to annotator biases and task artifacts, leading to different interpretations of the label distribution. We explore two modeling approaches for detecting items with potential disagreement: a 4-way classification with a “Complicated” label in addition to the three standard NLI labels, and a multilabel classification approach. We found that the multilabel classification is more expressive and gives better recall of the possible interpretations in the data.more » « less
-
Given raster imagery features and imperfect vector training labels with registration uncertainty, this paper studies a deep learning framework that can quantify and reduce the registration uncertainty of training labels as well as train neural network parameters simultaneously. The problem is important in broad applications such as streamline classification on Earth imagery or tissue segmentation on medical imagery, whereby annotating precise vector labels is expensive and time-consuming. However, the problem is challenging due to the gap between the vector representation of class labels and the raster representation of image features and the need for training neural networks with uncertain label locations. Existing research on uncertain training labels often focuses on uncertainty in label class semantics or characterizes label registration uncertainty at the pixel level (not contiguous vectors). To fill the gap, this paper proposes a novel learning framework that explicitly quantifies vector labels' registration uncertainty. We propose a registration-uncertainty-aware loss function and design an iterative uncertainty reduction algorithm by re-estimating the posterior of true vector label locations distribution based on a Gaussian process. Evaluations on real-world datasets in National Hydrography Dataset refinement show that the proposed approach significantly outperforms several baselines in the registration uncertainty estimations performance and classification performance.more » « less
-
Concentration of measure has been argued to be the fundamental cause of adversarial vulnerability. Mahloujifar et al. (2019) presented an empirical way to measure the concentration of a data distribution using samples, and employed it to find lower bounds on intrinsic robustness for several benchmark datasets. However, it remains unclear whether these lower bounds are tight enough to provide a useful approximation for the intrinsic robustness of a dataset. To gain a deeper understanding of the concentration of measure phenomenon, we first extend the Gaussian Isoperimetric Inequality to non-spherical Gaussian measures and arbitrary ℓp-norms (p ≥ 2). We leverage these theoretical insights to design a method that uses half-spaces to estimate the concentration of any empirical dataset under ℓp-norm distance metrics. Our proposed algorithm is more efficient than Mahloujifar et al. (2019)‘s, and experiments on synthetic datasets and image benchmarks demonstrate that it is able to find much tighter intrinsic robustness bounds. These tighter estimates provide further evidence that rules out intrinsic dataset concentration as a possible explanation for the adversarial vulnerability of state-of-the-art classifiers.more » « less
-
Existing approaches for multi-label classification are trained offline, missing the opportunity to adapt to new data instances as they become available. To address this gap, an online multi-label classification method was proposed recently, to learn from data instances sequentially. In this work, we focus on multi-label classification tasks, in which the labels are organized in a hierarchy. We formulate online hierarchical multi-labeled classification as an online optimization task that jointly learns individual label predictors and a label threshold, and propose a novel hierarchy constraint to penalize predictions that are inconsistent with the label hierarchy structure. Experimental results on three benchmark datasets show that the proposed approach outperforms online multi-label classification methods, and achieves comparable to, or even better performance than offline hierarchical classification frameworks with respect to hierarchical evaluation metrics.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
