{"total":86,"rows":[{"id":"2108.13897","title":"mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset","created":"2021-08-31","cited_by_count":116,"area":null},{"id":"2105.09680","title":"KLUE: Korean Language Understanding Evaluation","created":"2021-05-20","cited_by_count":114,"area":null},{"id":"2107.03158","title":"A Survey on Data Augmentation for Text Classification","created":"2021-07-07","cited_by_count":111,"area":null},{"id":"2106.07499","title":"An Empirical Survey of Data Augmentation for Limited Data Learning in NLP","created":"2021-06-14","cited_by_count":101,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2208.11857","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","created":"2022-08-25","cited_by_count":85,"area":null},{"id":"2110.01852","title":"Data Augmentation Approaches in Natural Language Processing: A Survey","created":"2021-10-05","cited_by_count":82,"area":null},{"id":"2105.00071","title":"Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark","created":"2021-04-30","cited_by_count":77,"area":null},{"id":"2105.03519","title":"Understanding by Understanding Not: Modeling Negation in Language Models","created":"2021-05-07","cited_by_count":73,"area":null},{"id":"2107.07150","title":"Tailor: Generating and Perturbing Text with Semantic Controls","created":"2021-07-15","cited_by_count":68,"area":null},{"id":"2110.01518","title":"Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics","created":"2021-10-04","cited_by_count":67,"area":null},{"id":"2101.03453","title":"BERT & Family Eat Word Salad: Experiments with Text Understanding","created":"2021-01-10","cited_by_count":44,"area":null},{"id":"2107.00753","title":"An Investigation of the (In)effectiveness of Counterfactually Augmented Data","created":"2021-07-01","cited_by_count":42,"area":null},{"id":"2405.09591","title":"A Comprehensive Survey on Data Augmentation","created":"2024-05-15","cited_by_count":40,"area":null},{"id":"2205.06009","title":"Falsesum: Generating Document-level NLI Examples for Recognizing Factual Inconsistency in Summarization","created":"2022-05-12","cited_by_count":34,"area":null},{"id":"2210.16952","title":"Transfer Learning with Synthetic Corpora for Spatial Role Labeling and Reasoning","created":"2022-10-30","cited_by_count":34,"area":"lr"},{"id":"2106.00149","title":"HiddenCut: Simple Data Augmentation for Natural Language Understanding with Better Generalization","created":"2021-05-31","cited_by_count":32,"area":null},{"id":"2104.07179","title":"Does Putting a Linguist in the Loop Improve NLU Data Collection?","created":"2021-04-15","cited_by_count":29,"area":null},{"id":"2104.08142","title":"Supervising Model Attention with Human Explanations for Robust Natural Language Inference","created":"2021-04-16","cited_by_count":29,"area":null},{"id":"2110.07596","title":"Retrieval-guided Counterfactual Generation for QA","created":"2021-10-14","cited_by_count":29,"area":null},{"id":"2105.05541","title":"Evaluating Gender Bias in Natural Language Inference","created":"2021-05-12","cited_by_count":27,"area":null},{"id":"2212.10898","title":"Training language models to summarize narratives improves brain alignment","created":"2022-12-21","cited_by_count":26,"area":null},{"id":"2101.00411","title":"Substructure Substitution: Structured Data Augmentation for NLP","created":"2021-01-02","cited_by_count":25,"area":null},{"id":"2204.09867","title":"A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generation","created":"2022-04-21","cited_by_count":25,"area":null},{"id":"2109.04144","title":"Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning","created":"2021-09-09","cited_by_count":23,"area":null},{"id":"2107.11610","title":"Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition","created":"2021-07-24","cited_by_count":19,"area":null},{"id":"2109.04947","title":"Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding","created":"2021-09-10","cited_by_count":19,"area":null},{"id":"2110.07159","title":"Interpreting the Robustness of Neural NLP Models to Textual Perturbations","created":"2021-10-14","cited_by_count":17,"area":null},{"id":"2110.08555","title":"On the Robustness of Reading Comprehension Models to Entity Renaming","created":"2021-10-16","cited_by_count":17,"area":null},{"id":"2206.02457","title":"Improving Contrastive Learning of Sentence Embeddings with Case-Augmented Positives and Retrieved Negatives","created":"2022-06-06","cited_by_count":16,"area":null},{"id":"2101.10713","title":"Exploring Transitivity in Neural NLI Models through Veridicality","created":"2021-01-26","cited_by_count":15,"area":null},{"id":"2109.01758","title":"Data Augmentation for Cross-Domain Named Entity Recognition","created":"2021-09-04","cited_by_count":14,"area":null},{"id":"2208.02080","title":"A Feature-space Multimodal Data Augmentation Technique for Text-video Retrieval","created":"2022-08-03","cited_by_count":13,"area":null},{"id":"2105.12932","title":"Contrastive Fine-tuning Improves Robustness for Neural Rankers","created":"2021-05-27","cited_by_count":12,"area":null},{"id":"2206.01909","title":"Toward Learning Robust and Invariant Representations with Alignment Regularization and Data Augmentation","created":"2022-06-04","cited_by_count":11,"area":null},{"id":"2108.11703","title":"Data Augmentation for Low-Resource Named Entity Recognition Using Backtranslation","created":"2021-08-26","cited_by_count":10,"area":null},{"id":"2209.05297","title":"DoubleMix: Simple Interpolation-Based Data Augmentation for Text Classification","created":"2022-09-12","cited_by_count":10,"area":null},{"id":"2212.05421","title":"Feature-Level Debiased Natural Language Understanding","created":"2022-12-11","cited_by_count":10,"area":null},{"id":"2305.16663","title":"GDA: Generative Data Augmentation Techniques for Relation Extraction Tasks","created":"2023-05-26","cited_by_count":10,"area":null},{"id":"2112.09237","title":"PECO: Examining Single Sentence Label Leakage in Natural Language Inference Datasets through Progressive Evaluation of Cluster Outliers","created":"2021-12-16","cited_by_count":8,"area":null},{"id":"2305.07984","title":"SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples","created":"2023-05-13","cited_by_count":8,"area":null},{"id":"2502.11671","title":"Diversity-oriented Data Augmentation with Large Language Models","created":"2025-02-17","cited_by_count":7,"area":null},{"id":"2210.10343","title":"Entity-to-Text based Data Augmentation for various Named Entity Recognition Tasks","created":"2022-10-19","cited_by_count":6,"area":null},{"id":"2312.04720","title":"From Big to Small Without Losing It All: Text Augmentation with ChatGPT for Efficient Sentiment Analysis","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2109.04922","title":"Beyond the Tip of the Iceberg: Assessing Coherence of Text Classifiers","created":"2021-09-10","cited_by_count":5,"area":null},{"id":"2109.05793","title":"Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models","created":"2021-09-13","cited_by_count":5,"area":null},{"id":"2202.02432","title":"Transformers and the representation of biomedical background knowledge","created":"2022-02-04","cited_by_count":5,"area":null},{"id":"2202.03611","title":"Do Language Models Learn Position-Role Mappings?","created":"2022-02-08","cited_by_count":5,"area":null},{"id":"2310.15010","title":"Statistical Depth for Ranking and Characterizing Transformer-Based Text Embeddings","created":"2023-10-23","cited_by_count":5,"area":null},{"id":"2310.16955","title":"Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attacks","created":"2023-10-25","cited_by_count":5,"area":null},{"id":"2403.00037","title":"Evolving to the Future: Unseen Event Adaptive Fake News Detection on Social Media","created":"2024-02-29","cited_by_count":5,"area":null},{"id":"2112.08609","title":"DuQM: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models","created":"2021-12-16","cited_by_count":4,"area":null},{"id":"2207.13948","title":"An Interpretability Evaluation Benchmark for Pre-trained Language Models","created":"2022-07-28","cited_by_count":4,"area":null},{"id":"2209.07879","title":"Less is Better: Recovering Intended-Feature Subspace to Robustify NLU Models","created":"2022-09-16","cited_by_count":4,"area":null},{"id":"2210.14957","title":"Disentangled Text Representation Learning with Information-Theoretic Perspective for Adversarial Robustness","created":"2022-10-26","cited_by_count":4,"area":null},{"id":"2401.13085","title":"IndiText Boost: Text Augmentation for Low Resource India Languages","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2408.04246","title":"Explicating the Implicit: Argument Detection Beyond Sentence Boundaries","created":"2024-08-08","cited_by_count":4,"area":null},{"id":"2502.14734","title":"Sentence Smith: Controllable Edits for Evaluating Text Embeddings","created":"2025-02-20","cited_by_count":4,"area":null},{"id":"2505.20209","title":"Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data Selection","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2203.10483","title":"Entailment Relation Aware Paraphrase Generation","created":"2022-03-20","cited_by_count":3,"area":null},{"id":"2211.03862","title":"Looking at the Overlooked: An Analysis on the Word-Overlap Bias in Natural Language Inference","created":"2022-11-07","cited_by_count":3,"area":null},{"id":"2402.08382","title":"Punctuation Restoration Improves Structure Understanding Without Supervision","created":"2024-02-13","cited_by_count":3,"area":null},{"id":"2404.13390","title":"Explanation based Bias Decoupling Regularization for Natural Language Inference","created":"2024-04-20","cited_by_count":3,"area":null},{"id":"2407.21073","title":"Enhancing Adversarial Text Attacks on BERT Models with Projected Gradient Descent","created":"2024-07-29","cited_by_count":3,"area":null},{"id":"2408.16756","title":"How Well Do LLMs Handle Cantonese? Benchmarking Cantonese Capabilities of Large Language Models","created":"2024-08-29","cited_by_count":3,"area":null},{"id":"2106.01635","title":"Can vectors read minds better than experts? Comparing data augmentation strategies for the automated scoring of children's mindreading ability","created":"2021-06-03","cited_by_count":2,"area":null},{"id":"2111.05196","title":"NATURE: Natural Auxiliary Text Utterances for Realistic Spoken Language Evaluation","created":"2021-11-09","cited_by_count":2,"area":null},{"id":"2204.02633","title":"DAGAM: Data Augmentation with Generation And Modification","created":"2022-04-06","cited_by_count":2,"area":null},{"id":"2302.11412","title":"Data Augmentation for Neural NLP","created":"2023-02-22","cited_by_count":2,"area":null},{"id":"2302.14413","title":"SMoA: Sparse Mixture of Adapters to Mitigate Multiple Dataset Biases","created":"2023-02-28","cited_by_count":2,"area":null},{"id":"2309.09380","title":"Mitigating Shortcuts in Language Models with Soft Label Encoding","created":"2023-09-17","cited_by_count":2,"area":null},{"id":"2403.08425","title":"Specification Overfitting in Artificial Intelligence","created":"2024-03-13","cited_by_count":2,"area":null},{"id":"2409.06803","title":"Decomposition of surprisal: Unified computational model of ERP components in language processing","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2507.05527","title":"Mitigating Shortcut Learning with InterpoLated Learning","created":"2025-07-07","cited_by_count":2,"area":null},{"id":"2305.15130","title":"On Degrees of Freedom in Defining and Testing Natural Language Understanding","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2309.12689","title":"AMPLIFY:Attention-based Mixup for Performance Improvement and Label Smoothing in Transformer","created":"2023-09-22","cited_by_count":1,"area":null},{"id":"2506.14613","title":"When Does Meaning Backfire? Investigating the Role of AMRs in NLI","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2508.06886","title":"Score Before You Speak: Improving Persona Consistency in Dialogue Generation using Response Quality Scores","created":"2025-08-09","cited_by_count":1,"area":null},{"id":"2601.19926","title":"The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2206.00192","title":"Order-sensitive Shapley Values for Evaluating Conceptual Soundness of NLP Models","created":"2022-06-01","cited_by_count":0,"area":null},{"id":"2306.04523","title":"Can current NLI systems handle German word order? Investigating language model performance on a new German challenge set of minimal pairs","created":"2023-06-07","cited_by_count":0,"area":null},{"id":"2307.10457","title":"Improving the Reusability of Pre-trained Language Models in Real-world Applications","created":"2023-07-19","cited_by_count":0,"area":null},{"id":"2312.06309","title":"An unsupervised learning approach to evaluate questionnaire data -- what one can learn from violations of measurement invariance","created":"2023-12-11","cited_by_count":0,"area":null},{"id":"2404.09830","title":"Negation Triplet Extraction with Syntactic Dependency and Semantic Consistency","created":"2024-04-15","cited_by_count":0,"area":null},{"id":"2605.23440","title":"SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2610.16547","title":"Know Yourself and Know Your Neighbour: A Syntactically Informed Self-Supervised Compositional Sentence Representation Learning Framework using a Recursive Hypernetwork","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}