{"total":64,"rows":[{"id":"2306.09479","title":"Inverse Scaling: When Bigger Isn't Better","created":"2023-06-15","cited_by_count":207,"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":"2306.04618","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","created":"2023-06-07","cited_by_count":97,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"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":"2305.17256","title":"Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning","created":"2023-05-26","cited_by_count":69,"area":null},{"id":"2211.00151","title":"A Close Look into the Calibration of Pre-trained Language Models","created":"2022-10-31","cited_by_count":57,"area":null},{"id":"2201.10766","title":"A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes","created":"2022-01-26","cited_by_count":56,"area":null},{"id":"2311.08648","title":"Explore Spurious Correlations at the Concept Level in Language Models for Text Classification","created":"2023-11-15","cited_by_count":48,"area":null},{"id":"2306.14321","title":"RobuT: A Systematic Study of Table QA Robustness Against Human-Annotated Adversarial Perturbations","created":"2023-06-25","cited_by_count":43,"area":null},{"id":"2203.12918","title":"A Rationale-Centric Framework for Human-in-the-loop Machine Learning","created":"2022-03-24","cited_by_count":27,"area":null},{"id":"2310.08256","title":"Impact of Co-occurrence on Factual Knowledge of Large Language Models","created":"2023-10-12","cited_by_count":19,"area":null},{"id":"2508.21456","title":"Morae: Proactively Pausing UI Agents for User Choices","created":"2025-08-29","cited_by_count":19,"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":"2210.11560","title":"Finding Dataset Shortcuts with Grammar Induction","created":"2022-10-20","cited_by_count":15,"area":null},{"id":"2305.18451","title":"Shift-Robust Molecular Relational Learning with Causal Substructure","created":"2023-05-29","cited_by_count":15,"area":null},{"id":"2310.20093","title":"Evaluating Neural Language Models as Cognitive Models of Language Acquisition","created":"2023-10-31","cited_by_count":15,"area":null},{"id":"2412.13989","title":"What makes a good metric? Evaluating automatic metrics for text-to-image consistency","created":"2024-12-18","cited_by_count":12,"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":"2310.18360","title":"Guiding LLM to Fool Itself: Automatically Manipulating Machine Reading Comprehension Shortcut Triggers","created":"2023-10-24","cited_by_count":10,"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":"2305.16490","title":"Prototype-Based Interpretability for Legal Citation Prediction","created":"2023-05-25","cited_by_count":9,"area":null},{"id":"2308.03228","title":"Why Linguistics Will Thrive in the 21st Century: A Reply to Piantadosi (2023)","created":"2023-08-06","cited_by_count":9,"area":null},{"id":"2408.12263","title":"Toward the Evaluation of Large Language Models Considering Score Variance across Instruction Templates","created":"2024-08-22","cited_by_count":7,"area":null},{"id":"2602.05910","title":"Chunky Post-Training: Data Driven Failures of Generalization","created":"2026-02-05","cited_by_count":7,"area":null},{"id":"2308.11043","title":"Spurious Correlations and Where to Find Them","created":"2023-08-21","cited_by_count":6,"area":null},{"id":"2310.12620","title":"Predict the Future from the Past? On the Temporal Data Distribution Shift in Financial Sentiment Classifications","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2412.04642","title":"Improving LLM Group Fairness on Tabular Data via In-Context Learning","created":"2024-12-05","cited_by_count":6,"area":null},{"id":"2305.16863","title":"Controlling Learned Effects to Reduce Spurious Correlations in Text Classifiers","created":"2023-05-26","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":"2412.07675","title":"RAZOR: Sharpening Knowledge by Cutting Bias with Unsupervised Text Rewriting","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2505.06032","title":"Short-circuiting Shortcuts: Mechanistic Investigation of Shortcuts in Text Classification","created":"2025-05-09","cited_by_count":5,"area":null},{"id":"2506.11111","title":"Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions","created":"2025-06-08","cited_by_count":5,"area":null},{"id":"2209.01824","title":"A Survey on Measuring and Mitigating Reasoning Shortcuts in Machine Reading Comprehension","created":"2022-09-05","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":"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":"2212.06711","title":"On Text-based Personality Computing: Challenges and Future Directions","created":"2022-12-13","cited_by_count":3,"area":null},{"id":"2305.05402","title":"Consistent Text Categorization using Data Augmentation in e-Commerce","created":"2023-05-09","cited_by_count":3,"area":null},{"id":"2306.11386","title":"Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation Extraction","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2411.08506","title":"Towards Operationalizing Right to Data Protection","created":"2024-11-13","cited_by_count":3,"area":null},{"id":"2309.04162","title":"GLS-CSC: A Simple but Effective Strategy to Mitigate Chinese STM Models' Over-Reliance on Superficial Clue","created":"2023-09-08","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":"2312.09718","title":"Discovering Highly Influential Shortcut Reasoning: An Automated Template-Free Approach","created":"2023-12-15","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":"2404.11276","title":"Towards Data-Centric Automatic R&D","created":"2024-04-17","cited_by_count":2,"area":null},{"id":"2504.01450","title":"CASCADE Your Datasets for Cross-Mode Knowledge Retrieval of Language Models","created":"2025-04-02","cited_by_count":2,"area":null},{"id":"2505.22829","title":"Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2602.01618","title":"SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia","created":"2026-02-02","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":"2310.13610","title":"Make Your Decision Convincing! A Unified Two-Stage Framework: Self-Attribution and Decision-Making","created":"2023-10-20","cited_by_count":1,"area":null},{"id":"2310.19986","title":"Addressing Weak Decision Boundaries in Image Classification by Leveraging Web Search and Generative Models","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2311.01655","title":"Detecting Spurious Correlations via Robust Visual Concepts in Real and AI-Generated Image Classification","created":"2023-11-03","cited_by_count":1,"area":null},{"id":"2402.06220","title":"A Unified Causal View of Instruction Tuning","created":"2024-02-09","cited_by_count":1,"area":null},{"id":"2402.14187","title":"From Adoption to Adaption: Tracing the Diffusion of New Emojis on Twitter","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2411.06040","title":"CGLearn: Consistent Gradient-Based Learning for Out-of-Distribution Generalization","created":"2024-11-09","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":"2411.04649","title":"DISCO: DISCovering Overfittings as Causal Rules for Text Classification Models","created":"2024-11-07","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":"2511.10120","title":"Generalizing to Unseen Disaster Events: A Causal View","created":"2025-11-13","cited_by_count":0,"area":null},{"id":"2602.06924","title":"Rank-Constrained Adaptation for Reliable Real-World Performance","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2604.12277","title":"Models Know Their Shortcuts: Deployment-Time Shortcut Mitigation","created":"2026-04-14","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},{"id":"2608.25028","title":"Behind the [MASK]: Disentangling Representation and Faithfulness in DAPF-Based Dementia Detection","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}