Finding Dataset Shortcuts with Grammar Induction (2022.emnlp-main)

Copied to clipboard

Challenge: Prior work on shortcut detection focused on enumerating features like unigrams or bigrams . prior work relied on post-hoc models that reveal qualitative patterns without a clear statistical interpretation .
Approach: They propose to use probabilistic grammars to characterize and discover shortcuts in NLP datasets using context-free grammars and synchronous context- free grammars.
Outcome: The proposed grammars reveal interesting shortcut features in a number of datasets, including simple and high-level features, and automatically identify groups of test examples on which conventional classifiers fail.

Similar Papers

Discovering Highly Influential Shortcut Reasoning: An Automated Template-Free Approach (2023.findings-emnlp)

Copied to clipboard

Challenge: Shortcut reasoning is an irrational process of inference, which degrades the robustness of an NLP model.
Approach: They propose a method to quantify the severity of shortcut reasoning by leveraging out-of-distribution data.
Outcome: The proposed method quantifies the severity of the discovered shortcut reasoning using out-of-distribution data.
Categorial Grammar Induction with Stochastic Category Selection (2024.lrec-main)

Copied to clipboard

Challenge: categorial grammar inducers have been used to learn from raw data, but they use shortcuts to ensure branching behavior.
Approach: They propose a grammar inducer that learns from raw data and does not rely on bias terms . they show a recall-homogeneity of 0.48 on a corpus of English child-directed speech .
Outcome: The proposed model achieves a recall-homogeneity of 0.48 on a corpus of English child-directed speech .
Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Language models (LMs) often rely on spurious correlations rather than causally relevant features to improve accuracy and generalizability.
Approach: They propose a benchmark that categorizes shortcuts into occurrence, style, and concept . they aim to explore the nuanced ways shortcuts influence the performance of LMs .
Outcome: The proposed benchmark categorizes shortcuts into occurrence, style, and concept . it systematically investigates models’ resilience and susceptibilities to sophisticated shortcuts .
Supervised and Unsupervised Probing of Shortcut Learning: Case Study on the Emergence and Evolution of Syntactic Heuristics in BERT (2025.findings-acl)

Copied to clipboard

Challenge: Contemporary language models (LMs) rely on shortcut learning, using superficial cues that are spuriously correlated with labels.
Approach: They propose to use syntactic heuristics to learn shortcuts in BERT when performing a task in Natural Language Understanding to investigate where these shortcuts emerge, how they evolve and how they impact the latent knowledge of the LM.
Outcome: The proposed model rely on syntactic heuristics when performing a task in Natural Language Understanding.
Compound Probabilistic Context-Free Grammars for Grammar Induction (P19-1)

Copied to clipboard

Challenge: Existing approaches to grammar induction have resorted to manually-engineered features and auxiliary objectives to induce the desired structures.
Approach: They propose a formalization of the grammar induction problem that models sentences as being generated by a compound probabilistic context free grammar.
Outcome: Experiments on English and Chinese show that the proposed approach is more efficient than other methods.
Categorial grammar induction from raw data (2023.findings-acl)

Copied to clipboard

Challenge: a new model for categorial grammar induction is based on raw data without part-of-speech information.
Approach: They propose a grammar induction model that learns from raw data without part-of-speech information.
Outcome: a new model for inducing a basic categorial grammar is developed . the model attains a recall-homogeneity of 0.33 on average, and a bias toward forward function application is added .
Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models (2022.findings-naacl)

Copied to clipboard

Challenge: Existing work identifies task-specific shortcuts via human priors or error analyses, which requires extensive expertise and efforts.
Approach: They propose to automatically identify spurious correlations in NLP models at scale by using existing interpretability methods to extract tokens that significantly affect model’s decision process.
Outcome: The proposed method can identify spurious correlations in NLP models at scale and mitigate these leads to more robust models in multiple applications.
Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown remarkable capabilities in various tasks, but may rely on dataset biases as shortcuts for prediction.
Approach: They propose to use a test suite to evaluate the impact of shortcuts on LLMs' performance.
Outcome: The proposed test suite incorporates six shortcut types, five evaluation metrics, and four prompting strategies.
HiddenCut: Simple Data Augmentation for Natural Language Understanding with Better Generalizability (2021.acl-long)

Copied to clipboard

Challenge: Using data augmentation to fine-tune pre-trained models with task-specific data has been shown to be ineffective and redundant during fine-timing.
Approach: They propose a data augmentation technique to regularize pre-trained models and encourage them to learn more generalizable features by dropping contiguous spans during training.
Outcome: The proposed method outperforms state-of-the-art methods on the GLUE benchmark and consistently exhibits superior generalization performances on out-of distribution and challenging counterexamples.
ListOps: A Diagnostic Dataset for Latent Tree Learning (N18-4)

Copied to clipboard

Challenge: Existing work on latent tree learning models shows they do not learn plausible grammars . a dataset is created to study the parsing ability of such models in natural language .
Approach: They propose a toy dataset to study the parsing ability of latent tree learning models . they propose 'listops' toy that has a single correct parse strategy that a system needs to learn .
Outcome: The proposed model outperforms existing models on sentence understanding tasks . it can learn grammars that conform to plausible semantics and syntactic formalisms .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations