{"total":90,"rows":[{"id":"2401.00595","title":"State of What Art? A Call for Multi-Prompt LLM Evaluation","created":"2023-12-31","cited_by_count":310,"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":"2211.08073","title":"GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective","created":"2022-11-15","cited_by_count":72,"area":null},{"id":"2305.14938","title":"Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark","created":"2023-05-24","cited_by_count":63,"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":"2404.16966","title":"Examining the robustness of LLM evaluation to the distributional assumptions of benchmarks","created":"2024-04-25","cited_by_count":31,"area":null},{"id":"2307.10168","title":"LLMs as Workers in Human-Computational Algorithms? Replicating Crowdsourcing Pipelines with LLMs","created":"2023-07-19","cited_by_count":27,"area":null},{"id":"2210.04873","title":"CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation","created":"2022-10-10","cited_by_count":24,"area":null},{"id":"2207.02159","title":"Robustness Analysis of Video-Language Models Against Visual and Language Perturbations","created":"2022-07-05","cited_by_count":23,"area":null},{"id":"2210.04675","title":"A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processing","created":"2022-10-10","cited_by_count":21,"area":null},{"id":"2403.07937","title":"Speech Robust Bench: A Robustness Benchmark For Speech Recognition","created":"2024-03-08","cited_by_count":21,"area":null},{"id":"2404.04963","title":"SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials","created":"2024-04-07","cited_by_count":20,"area":null},{"id":"2407.12858","title":"Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)","created":"2024-07-10","cited_by_count":20,"area":null},{"id":"2404.09135","title":"Unveiling LLM Evaluation Focused on Metrics: Challenges and Solutions","created":"2024-04-14","cited_by_count":18,"area":null},{"id":"2212.11237","title":"Not Just Pretty Pictures: Toward Interventional Data Augmentation Using Text-to-Image Generators","created":"2022-12-21","cited_by_count":17,"area":null},{"id":"2504.02733","title":"Enhancing LLM Robustness to Perturbed Instructions: An Empirical Study","created":"2025-04-03","cited_by_count":17,"area":null},{"id":"2403.10144","title":"NLP Verification: Towards a General Methodology for Certifying Robustness","created":"2024-03-15","cited_by_count":16,"area":null},{"id":"2406.17813","title":"Unsupervised Concept Drift Detection from Deep Learning Representations in Real-time","created":"2024-06-24","cited_by_count":16,"area":null},{"id":"2502.10996","title":"RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation","created":"2025-02-16","cited_by_count":16,"area":null},{"id":"2312.07492","title":"SocialStigmaQA: A Benchmark to Uncover Stigma Amplification in Generative Language Models","created":"2023-12-12","cited_by_count":15,"area":null},{"id":"2407.06992","title":"Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspective","created":"2024-07-09","cited_by_count":15,"area":null},{"id":"2410.21331","title":"Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness","created":"2024-10-27","cited_by_count":13,"area":null},{"id":"2308.07902","title":"Through the Lens of Core Competency: Survey on Evaluation of Large Language Models","created":"2023-08-15","cited_by_count":12,"area":null},{"id":"2210.10693","title":"Robustness of Demonstration-based Learning Under Limited Data Scenario","created":"2022-10-19","cited_by_count":11,"area":null},{"id":"2210.12813","title":"TAPE: Assessing Few-shot Russian Language Understanding","created":"2022-10-23","cited_by_count":11,"area":null},{"id":"2306.00168","title":"Measuring the Robustness of NLP Models to Domain Shifts","created":"2023-05-31","cited_by_count":11,"area":null},{"id":"2311.01307","title":"The Effect of Scaling, Retrieval Augmentation and Form on the Factual Consistency of Language Models","created":"2023-11-02","cited_by_count":11,"area":null},{"id":"2209.03742","title":"SynSciPass: detecting appropriate uses of scientific text generation","created":"2022-09-07","cited_by_count":10,"area":null},{"id":"2506.23111","title":"FairI Tales: Evaluation of Fairness in Indian Contexts with a Focus on Bias and Stereotypes","created":"2025-06-29","cited_by_count":9,"area":null},{"id":"2302.04618","title":"Robust Question Answering against Distribution Shifts with Test-Time Adaptation: An Empirical Study","created":"2023-02-09","cited_by_count":8,"area":null},{"id":"2305.16444","title":"Don't Retrain, Just Rewrite: Countering Adversarial Perturbations by Rewriting Text","created":"2023-05-25","cited_by_count":8,"area":null},{"id":"2210.12674","title":"Towards Generalizable and Robust Text-to-SQL Parsing","created":"2022-10-23","cited_by_count":7,"area":null},{"id":"2305.04003","title":"ANTONIO: Towards a Systematic Method of Generating NLP Benchmarks for Verification","created":"2023-05-06","cited_by_count":6,"area":null},{"id":"2306.06779","title":"Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering","created":"2023-06-11","cited_by_count":6,"area":null},{"id":"2308.11284","title":"LEAP: Efficient and Automated Test Method for NLP Software","created":"2023-08-22","cited_by_count":6,"area":null},{"id":"2309.06358","title":"Generative Data Augmentation using LLMs improves Distributional Robustness in Question Answering","created":"2023-09-03","cited_by_count":6,"area":null},{"id":"2310.07299","title":"RobustGEC: Robust Grammatical Error Correction Against Subtle Context Perturbation","created":"2023-10-11","cited_by_count":6,"area":null},{"id":"2311.08662","title":"Evaluating Concurrent Robustness of Language Models Across Diverse Challenge Sets","created":"2023-11-15","cited_by_count":6,"area":null},{"id":"2405.14646","title":"Unveiling the Achilles' Heel of NLG Evaluators: A Unified Adversarial Framework Driven by Large Language Models","created":"2024-05-23","cited_by_count":6,"area":null},{"id":"2311.00508","title":"Robustness Tests for Automatic Machine Translation Metrics with Adversarial Attacks","created":"2023-11-01","cited_by_count":5,"area":null},{"id":"2311.09694","title":"Whispers of Doubt Amidst Echoes of Triumph in NLP Robustness","created":"2023-11-16","cited_by_count":5,"area":null},{"id":"2408.05874","title":"LLM-Based Robust Product Classification in Commerce and Compliance","created":"2024-08-11","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":"2210.13439","title":"Cascading Biases: Investigating the Effect of Heuristic Annotation Strategies on Data and Models","created":"2022-10-24","cited_by_count":4,"area":null},{"id":"2302.00094","title":"The Impacts of Unanswerable Questions on the Robustness of Machine Reading Comprehension Models","created":"2023-01-31","cited_by_count":4,"area":null},{"id":"2303.00333","title":"Competence-Based Analysis of Language Models","created":"2023-03-01","cited_by_count":4,"area":null},{"id":"2308.10464","title":"Unsupervised Dialogue Topic Segmentation in Hyperdimensional Space","created":"2023-08-21","cited_by_count":4,"area":null},{"id":"2310.16959","title":"Improving Few-shot Generalization of Safety Classifiers via Data Augmented Parameter-Efficient Fine-Tuning","created":"2023-10-25","cited_by_count":4,"area":null},{"id":"2312.17591","title":"Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training","created":"2023-12-29","cited_by_count":4,"area":null},{"id":"2307.12507","title":"Gradient-Based Word Substitution for Obstinate Adversarial Examples Generation in Language Models","created":"2023-07-24","cited_by_count":3,"area":null},{"id":"2310.08008","title":"Effects of Human Adversarial and Affable Samples on BERT Generalization","created":"2023-10-12","cited_by_count":3,"area":null},{"id":"2402.02379","title":"Unveiling the Deficiencies of Pre-trained Text-and-Layout Models in Real-world Visually-rich Document Information Extraction","created":"2024-02-04","cited_by_count":3,"area":null},{"id":"2503.03417","title":"When Claims Evolve: Evaluating and Enhancing the Robustness of Embedding Models Against Misinformation Edits","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2506.03627","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2306.13971","title":"Towards Robust Aspect-based Sentiment Analysis through Non-counterfactual Augmentations","created":"2023-06-24","cited_by_count":2,"area":null},{"id":"2311.14837","title":"Benchmarking Robustness of Text-Image Composed Retrieval","created":"2023-11-24","cited_by_count":2,"area":null},{"id":"2311.17128","title":"Vulnerability Analysis of Transformer-based Optical Character Recognition to Adversarial Attacks","created":"2023-11-28","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":"2404.07135","title":"Towards Robustness of Text-to-Visualization Translation against Lexical and Phrasal Variability","created":"2024-04-10","cited_by_count":2,"area":null},{"id":"2505.19397","title":"Are Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domains","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2506.00358","title":"$\\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time","created":"2025-05-31","cited_by_count":2,"area":null},{"id":"2510.19641","title":"Style Attack Disguise: When Fonts Become a Camouflage for Adversarial Intent","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2305.12620","title":"Keeping Up with the Language Models: Systematic Benchmark Extension for Bias Auditing","created":"2023-05-22","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":"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":"2307.12221","title":"FATRER: Full-Attention Topic Regularizer for Accurate and Robust Conversational Emotion Recognition","created":"2023-07-23","cited_by_count":1,"area":null},{"id":"2310.01452","title":"Fooling the Textual Fooler via Randomizing Latent Representations","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2406.07444","title":"On the Robustness of Document-Level Relation Extraction Models to Entity Name Variations","created":"2024-06-11","cited_by_count":1,"area":null},{"id":"2503.23924","title":"Model Hemorrhage and the Robustness Limits of Large Language Models","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2509.01093","title":"Natural Context Drift Undermines the Natural Language Understanding of Large Language Models","created":"2025-09-01","cited_by_count":1,"area":null},{"id":"2206.14575","title":"Why Robust Natural Language Understanding is a Challenge","created":"2022-06-21","cited_by_count":0,"area":null},{"id":"2207.08943","title":"MRCLens: an MRC Dataset Bias Detection Toolkit","created":"2022-07-18","cited_by_count":0,"area":null},{"id":"2304.12764","title":"Test-Time Adaptation with Perturbation Consistency Learning","created":"2023-04-25","cited_by_count":0,"area":null},{"id":"2307.11316","title":"Making Pre-trained Language Models both Task-solvers and Self-calibrators","created":"2023-07-21","cited_by_count":0,"area":null},{"id":"2311.08705","title":"Evaluating Robustness of Dialogue Summarization Models in the Presence of Naturally Occurring Variations","created":"2023-11-15","cited_by_count":0,"area":null},{"id":"2312.12588","title":"An Empirical study of Unsupervised Neural Machine Translation: analyzing NMT output, model's behavior and sentences' contribution","created":"2023-12-19","cited_by_count":0,"area":null},{"id":"2312.16156","title":"From text to multimodal: a survey of adversarial example generation in question answering systems","created":"2023-12-26","cited_by_count":0,"area":null},{"id":"2404.05088","title":"How much reliable is ChatGPT's prediction on Information Extraction under Input Perturbations?","created":"2024-04-07","cited_by_count":0,"area":null},{"id":"2409.19766","title":"Towards Robust Extractive Question Answering Models: Rethinking the Training Methodology","created":"2024-09-29","cited_by_count":0,"area":null},{"id":"2410.13873","title":"On the Robustness of Machine Learning Models in Predicting Thermodynamic Properties: a Case of Searching for New Quasicrystal Approximants","created":"2024-10-02","cited_by_count":0,"area":null},{"id":"2508.18407","title":"Can Out-of-Distribution Evaluations Uncover Reliance on Shortcuts? A Case Study in Question Answering","created":"2025-08-25","cited_by_count":0,"area":null},{"id":"2510.21469","title":"Enhancing Social Robots through Resilient AI","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2511.07888","title":"Breaking the Adversarial Robustness-Performance Trade-off in Text Classification via Manifold Purification","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2512.06304","title":"Degrading Voice: A Comprehensive Overview of Robust Voice Conversion Through Input Manipulation","created":"2025-12-06","cited_by_count":0,"area":null},{"id":"2601.13122","title":"Responsible AI for General-Purpose Systems: Overview, Challenges, and A Path Forward","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2605.11502","title":"Robust Biomedical Publication Type and Study Design Classification with Knowledge-Guided Perturbations","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2607.25814","title":"Evaluation of Adversarial Robustness in Arabic Language Models","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.03842","title":"Sensitivity, Causality, and Repair Dissociate: A Layer-Wise Analysis of Perturbation Robustness and Its Scaling","created":"2026-08-04","cited_by_count":0,"area":null}],"next_cursor":null}