Lune

EMNLP2022Top-tier venue

Finding Dataset Shortcuts with Grammar Induction

Dan Friedman, Alexander Wettig, Danqi Chen

Abstract

Many NLP datasets have been found to contain shortcuts: simple decision rules that achieve surprisingly high accuracy. However, it is difficult to discover shortcuts automatically. Prior work on automatic shortcut detection has focused on enumerating features like unigrams or bigrams, which can find only low-level shortcuts, or relied on post-hoc model interpretability methods like saliency maps, which reveal qualitative patterns without a clear statistical interpretation. In this work, we propose to use probabilistic grammars to characterize and discover shortcuts in NLP datasets. Specifically, we use a contextfree grammar to model patterns in sentence classification datasets and use a synchronous context-free grammar to model datasets involving sentence pairs. The resulting grammars reveal interesting shortcut features in a number of datasets, including both simple and high-level features, and automatically identify groups of test examples on which conventional classifiers fail. Finally, we show that the features we discover can be used to generate diagnostic contrast examples and incorporated into standard robust optimization methods to improve worst-group accuracy. 1

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

3 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Evaluating Models' Local Decision Boundaries via Contrast Sets cites Learning The Difference That Makes A Difference With Counterfactually-Augmented Data
  • Grammar Prompting for Domain-Specific Language Generation with Large Language Models cites Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive Grammars
  • Explore Spurious Correlations at the Concept Level in Language Models for Text Classification cites Learning The Difference That Makes A Difference With Counterfactually-Augmented Data
  • Explore Spurious Correlations at the Concept Level in Language Models for Text Classification cites Just Train Twice: Improving Group Robustness without Training Group Information
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers3

  1. Grammar Prompting for Domain-Specific Language Generation with Large Language ModelsBailin Wang, Zi Wang, Xuezhi Wang, Yuan Cao et al.NeurIPS 2023 · 138 citations
  2. Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive GrammarsSonglin Yang, Roger Levy, Yoon KimACL 2023 · 1 citation
  3. Explore Spurious Correlations at the Concept Level in Language Models for Text ClassificationYuhang Zhou, Paiheng Xu, Xiaoyu Liu, Bang An et al.ACL 2024

Builds on10

  1. Just Train Twice: Improving Group Robustness without Training Group InformationEvan Zheran Liu, Behzad Haghgoo, Annie S. Chen, Aditi Raghunathan et al.ICML 2021 · 683 citations
  2. Learning The Difference That Makes A Difference With Counterfactually-Augmented DataDivyansh Kaushik, Eduard H. Hovy, Zachary Chase LiptonICLR 2020 · 625 citations
  3. Understanding Global Feature Contributions With Additive Importance MeasuresIan Covert, Scott M. Lundberg, Su-In LeeNeurIPS 2020 · 476 citations
  4. Evaluating Models' Local Decision Boundaries via Contrast SetsMatt Gardner, Yoav Artzi, Victoria Basmova, Jonathan Berant et al.EMNLP Findings 2020 · 260 citations
  5. Explaining Black Box Predictions and Unveiling Data Artifacts through Influence FunctionsXiaochuang Han, Byron C. Wallace, Yulia TsvetkovACL 2020 · 91 citations

Related papers

  1. Discovering Highly Influential Shortcut Reasoning: An Automated Template-Free ApproachDaichi Haraguchi, Kiyoaki Shirai, Naoya Inoue, Natthawut KertkeidkachornEMNLP Findings 2023
  2. Improving the robustness of NLI models with minimax trainingMichalis Korakakis, Andreas VlachosACL 2023 · 4 citations
  3. Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context LearningRuixiang Tang, Dehan Kong, Longtao Huang, Hui XueACL Findings 2023 · 31 citations
  4. Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language ModelsYuqing Zhou, Ruixiang Tang, Ziyu Yao, Ziwei ZhuEMNLP Findings 2024 · 3 citations
  5. Causally motivated multi-shortcut identification and removalJiayun Zheng, Maggie MakarNeurIPS 2022 · 27 citations
Dusk over the sea between two cliffs drawn in fine vertical lines