paper-with-me

홈 › Papers

Evaluating Models' Local Decision Boundaries via Contrast Sets

2020-04-06 · Findings of the Association for Computational Linguistics 2020 · Matt Gardner, Yoav Artzi, Victoria Basmova, Jonathan Berant, Ben Bogin, Sihao Chen, Pradeep Dasigi, Dheeru Dua, Yanai Elazar, Ananth Gottumukkala, Nitish Gupta, Hanna Hajishirzi, Gabriel Ilharco, Daniel Khashabi, Kevin Lin, Jiangming Liu, Nelson F. Liu, Phoebe Mulcaire, Qiang Ning, Sameer Singh, Noah A. Smith, Sanjay Subramanian, Reut Tsarfaty, Eric Wallace, Ally Zhang, Ben Zhou

Standard test sets for supervised learning evaluate in-distribution generalization. Unfortunately, when a dataset has systematic gaps (e.g., annotation artifacts), these evaluations are misleading: a model can learn simple decision rules that perform well on the test set but do not capture a dataset's intended capabilities. We propose a new annotation paradigm for NLP that helps to close systematic gaps in the test data. In particular, after a dataset is constructed, we recommend that the dataset authors manually perturb the test instances in small but meaningful ways that (typically) change the gold label, creating contrast sets. Contrast sets provide a local view of a model's decision boundary, which can be used to more accurately evaluate a model's true linguistic capabilities. We demonstrate the efficacy of contrast sets by creating them for 10 diverse NLP datasets (e.g., DROP reading comprehension, UD parsing, IMDb sentiment analysis). Although our contrast sets are not explicitly adversarial, model performance is significantly lower on them than on the original test sets---up to 25\% in some cases. We release our contrast sets as new evaluation benchmarks and encourage future dataset construction efforts to follow similar annotation processes.

📄 PDF Abstract BibTeX arXiv:2004.02709

Code (1)

allenai/contrast-sets 공식 구현

Tasks

Reading ComprehensionSentiment Analysis

Similar Papers 제목 키워드 기반

Enhancing NLP Robustness and Generalization through LLM-Generated Contrast Sets: A Scalable Framework for Systematic Evaluation and Adversarial Training

2025-03-09 · Hender Lin

Standard NLP benchmarks often fail to capture vulnerabilities stemming from dataset artifacts and spurious correlations. Contrast sets address this gap by challenging models near decision boundaries but are traditionally…

DiversitySystematic Generalization

Deep Clustering by Semantic Contrastive Learning

2021-03-03 · Jiabo Huang, Shaogang Gong

Whilst contrastive learning has recently brought notable benefits to deep clustering of unlabelled images by learning sample-specific discriminative visual features, its potential for explicitly inferring class decision …

ClusteringContrastive LearningDeep ClusteringObject Recognition+1

Loss Function Entropy Regularization for Diverse Decision Boundaries

2022-04-30 · Sue Sin Chong

Is it possible to train several classifiers to perform meaningful crowd-sourcing to produce a better prediction label set without ground-truth annotation? This paper will modify the contrastive learning objectives to aut…

Contrastive LearningDenoisingPredictionUnsupervised Image Classification

ROBY: Evaluating the Robustness of a Deep Model by its Decision Boundaries

2020-12-18 · Jinyin Chen, Zhen Wang, Haibin Zheng, Jun Xiao 외

With the successful application of deep learning models in many real-world tasks, the model robustness becomes more and more critical. Often, we evaluate the robustness of the deep models by attacking them with purposely…

Input Invex Neural Network

2021-06-16 · Suman Sapkota, Binod Bhattarai

Connected decision boundaries are useful in several tasks like image segmentation, clustering, alpha-shape or defining a region in nD-space. However, the machine learning literature lacks methods for generating connected…

Image ClassificationImage SegmentationSemantic Segmentation