{"total":59,"rows":[{"id":"2109.00725","title":"Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond","created":"2021-09-02","cited_by_count":178,"area":null},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107,"area":null},{"id":"2109.03795","title":"Desiderata for Representation Learning: A Causal Perspective","created":"2021-09-08","cited_by_count":76,"area":null},{"id":"2110.07736","title":"Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models","created":"2021-10-14","cited_by_count":76,"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":"2107.00520","title":"Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations","created":"2021-06-29","cited_by_count":41,"area":null},{"id":"2202.12350","title":"DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptation","created":"2022-02-24","cited_by_count":37,"area":null},{"id":"2302.04116","title":"Training-free Lexical Backdoor Attacks on Language Models","created":"2023-02-08","cited_by_count":31,"area":"safety"},{"id":"2210.14011","title":"Are All Spurious Features in Natural Language Alike? An Analysis through a Causal Lens","created":"2022-10-25","cited_by_count":28,"area":null},{"id":"2305.14910","title":"From Shortcuts to Triggers: Backdoor Defense with Denoised PoE","created":"2023-05-24","cited_by_count":27,"area":null},{"id":"2109.05213","title":"Uncovering Main Causalities for Long-tailed Information Extraction","created":"2021-09-11","cited_by_count":21,"area":null},{"id":"2204.12708","title":"On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations","created":"2022-04-27","cited_by_count":19,"area":null},{"id":"2107.04212","title":"Measuring and Improving Model-Moderator Collaboration using Uncertainty Estimation","created":"2021-07-09","cited_by_count":18,"area":null},{"id":"2210.01302","title":"Nuisances via Negativa: Adjusting for Spurious Correlations via Data Augmentation","created":"2022-10-04","cited_by_count":18,"area":null},{"id":"2205.12640","title":"Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing","created":"2022-05-25","cited_by_count":16,"area":null},{"id":"2208.09329","title":"Causal Intervention Improves Implicit Sentiment Analysis","created":"2022-08-19","cited_by_count":16,"area":null},{"id":"2210.11560","title":"Finding Dataset Shortcuts with Grammar Induction","created":"2022-10-20","cited_by_count":15,"area":null},{"id":"2209.15177","title":"Domain Generalization -- A Causal Perspective","created":"2022-09-30","cited_by_count":14,"area":null},{"id":"2110.00911","title":"Enhancing Model Robustness and Fairness with Causality: A Regularization Approach","created":"2021-10-03","cited_by_count":11,"area":null},{"id":"2201.00768","title":"Robust Natural Language Processing: Recent Advances, Challenges, and Future Directions","created":"2022-01-03","cited_by_count":11,"area":null},{"id":"2305.13654","title":"Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis","created":"2023-05-23","cited_by_count":11,"area":null},{"id":"2409.17455","title":"Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models","created":"2024-09-26","cited_by_count":10,"area":null},{"id":"2209.08799","title":"Probing Spurious Correlations in Popular Event-Based Rumor Detection Benchmarks","created":"2022-09-19","cited_by_count":7,"area":null},{"id":"2404.02356","title":"Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors","created":"2024-04-02","cited_by_count":7,"area":"moe"},{"id":"2109.03756","title":"Diagnostics-Guided Explanation Generation","created":"2021-09-08","cited_by_count":6,"area":null},{"id":"2310.11991","title":"Removing Spurious Concepts from Neural Network Representations via Joint Subspace Estimation","created":"2023-10-18","cited_by_count":6,"area":null},{"id":"2212.10392","title":"Debiasing Stance Detection Models with Counterfactual Reasoning and Adversarial Bias Learning","created":"2022-12-20","cited_by_count":5,"area":null},{"id":"2305.13685","title":"Causal Intervention for Abstractive Related Work Generation","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2410.22944","title":"Focus On This, Not That! Steering LLMs with Adaptive Feature Specification","created":"2024-10-30","cited_by_count":5,"area":null},{"id":"2502.11425","title":"Counterfactual-Consistency Prompting for Relative Temporal Understanding in Large Language Models","created":"2025-02-17","cited_by_count":5,"area":"lr"},{"id":"2310.17924","title":"SOUL: Towards Sentiment and Opinion Understanding of Language","created":"2023-10-27","cited_by_count":4,"area":null},{"id":"2401.09615","title":"Learning Shortcuts: On the Misleading Promise of NLU in Language Models","created":"2024-01-17","cited_by_count":4,"area":null},{"id":"2110.08931","title":"Quantifying the Task-Specific Information in Text-Based Classifications","created":"2021-10-17","cited_by_count":3,"area":null},{"id":"2302.09345","title":"Improving the Out-Of-Distribution Generalization Capability of Language Models: Counterfactually-Augmented Data is not Enough","created":"2023-02-18","cited_by_count":3,"area":null},{"id":"2311.06647","title":"Robust Text Classification: Analyzing Prototype-Based Networks","created":"2023-11-11","cited_by_count":3,"area":null},{"id":"2402.14536","title":"Domain Generalization via Causal Adjustment for Cross-Domain Sentiment Analysis","created":"2024-02-22","cited_by_count":3,"area":null},{"id":"2411.04090","title":"A Collaborative Content Moderation Framework for Toxicity Detection based on Conformalized Estimates of Annotation Disagreement","created":"2024-11-06","cited_by_count":3,"area":null},{"id":"2501.07305","title":"The Devil is in the Spurious Correlations: Boosting Moment Retrieval with Dynamic Learning","created":"2025-01-13","cited_by_count":3,"area":null},{"id":"2209.09630","title":"Detection of Malicious Websites Using Machine Learning Techniques","created":"2022-09-13","cited_by_count":2,"area":null},{"id":"2310.06666","title":"Unlock the Potential of Counterfactually-Augmented Data in Out-Of-Distribution Generalization","created":"2023-10-10","cited_by_count":2,"area":null},{"id":"2311.06549","title":"Zero-Shot Cross-Lingual Sentiment Classification under Distribution Shift: an Exploratory Study","created":"2023-11-11","cited_by_count":2,"area":null},{"id":"2406.18562","title":"Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation","created":"2024-05-28","cited_by_count":2,"area":null},{"id":"2502.21123","title":"Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models","created":"2025-02-28","cited_by_count":2,"area":null},{"id":"2205.10932","title":"Argumentative Explanations for Pattern-Based Text Classifiers","created":"2022-05-22","cited_by_count":1,"area":null},{"id":"2305.14104","title":"Out-of-Distribution Generalization in Text Classification: Past, Present, and Future","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2502.04022","title":"Quantification of Biodiversity from Historical Survey Text with LLM-based Best-Worst Scaling","created":"2025-02-06","cited_by_count":1,"area":null},{"id":"2508.21083","title":"CoBA: Counterbias Text Augmentation for Mitigating Various Spurious Correlations via Semantic Triples","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2605.02640","title":"Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2210.11805","title":"Robustifying Sentiment Classification by Maximally Exploiting Few Counterfactuals","created":"2022-10-21","cited_by_count":0,"area":null},{"id":"2406.12060","title":"Not Eliminate but Aggregate: Post-Hoc Control over Mixture-of-Experts to Address Shortcut Shifts in Natural Language Understanding","created":"2024-06-17","cited_by_count":0,"area":"moe"},{"id":"2410.08972","title":"ALVIN: Active Learning Via INterpolation","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2411.04649","title":"DISCO: DISCovering Overfittings as Causal Rules for Text Classification Models","created":"2024-11-07","cited_by_count":0,"area":null},{"id":"2412.20563","title":"Counterfactual Samples Constructing and Training for Commonsense Statements Estimation","created":"2024-12-29","cited_by_count":0,"area":null},{"id":"2502.18353","title":"DBR: Divergence-Based Regularization for Debiasing Natural Language Understanding Models","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2506.19680","title":"Model Guidance via Robust Feature Attribution","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2509.05230","title":"CURE: Controlled Unlearning for Robust Embeddings -- Mitigating Conceptual Shortcuts in Pre-Trained Language Models","created":"2025-09-05","cited_by_count":0,"area":"safety"},{"id":"2509.20587","title":"Unsupervised Domain Adaptation for Binary Classification with an Unobservable Source Subpopulation","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2602.20400","title":"Three Concrete Challenges and Two Hopes for the Safety of Unsupervised Elicitation","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2608.09209","title":"UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers","created":"2026-08-10","cited_by_count":0,"area":null}],"next_cursor":null}