Evaluating NLP Models via Contrast Sets
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Reading ComprehensionSentiment AnalysisSimilar Papers 제목 키워드 기반
Evaluating Large Language Models Using Contrast Sets: An Experimental Approach
In the domain of Natural Language Inference (NLI), especially in tasks involving the classification of multiple input texts, the Cross-Entropy Loss metric is widely employed as a standard for error measurement. However, …
Natural Language InferenceEnhancing NLP Robustness and Generalization through LLM-Generated Contrast Sets: A Scalable Framework for Systematic Evaluation and Adversarial Training
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 GeneralizationEvaluating Models' Local Decision Boundaries via Contrast Sets
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 simp…
Reading ComprehensionSentiment AnalysisEvaluating Causal Models by Comparing Interventional Distributions
The predominant method for evaluating the quality of causal models is to measure the graphical accuracy of the learned model structure. We present an alternative method for evaluating causal models that directly measures…
ERICA: Quantifying Replicability of Cluster Analysis
Despite being ubiquitous in science, clustering lacks a unified framework for quantitatively evaluating the replicability of its results. We present evaluating replicability via iterative clustering assignments (ERICA), …