{"total":45,"rows":[{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879,"area":null},{"id":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291,"area":null},{"id":"2105.09680","title":"KLUE: Korean Language Understanding Evaluation","created":"2021-05-20","cited_by_count":114,"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":"2104.05832","title":"SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoning","created":"2021-04-12","cited_by_count":77,"area":null},{"id":"2211.00295","title":"CONDAQA: A Contrastive Reading Comprehension Dataset for Reasoning about Negation","created":"2022-11-01","cited_by_count":39,"area":null},{"id":"2201.05729","title":"CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks","created":"2022-01-15","cited_by_count":32,"area":null},{"id":"2204.10496","title":"Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks","created":"2022-04-22","cited_by_count":23,"area":null},{"id":"2210.12517","title":"Exploring The Landscape of Distributional Robustness for Question Answering Models","created":"2022-10-22","cited_by_count":23,"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":"2209.07430","title":"Machine Reading, Fast and Slow: When Do Models \"Understand\" Language?","created":"2022-09-15","cited_by_count":13,"area":null},{"id":"2109.02837","title":"Exploring Strategies for Generalizable Commonsense Reasoning with Pre-trained Models","created":"2021-09-07","cited_by_count":11,"area":null},{"id":"2109.11256","title":"Can Question Generation Debias Question Answering Models? A Case Study on Question-Context Lexical Overlap","created":"2021-09-23","cited_by_count":8,"area":null},{"id":"2411.02018","title":"Shortcut Learning in In-Context Learning: A Survey","created":"2024-11-04","cited_by_count":8,"area":null},{"id":"2401.18001","title":"Desiderata for the Context Use of Question Answering Systems","created":"2024-01-31","cited_by_count":7,"area":null},{"id":"2404.12145","title":"From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2104.07646","title":"Are Multilingual BERT models robust? A Case Study on Adversarial Attacks for Multilingual Question Answering","created":"2021-04-15","cited_by_count":6,"area":null},{"id":"2302.11978","title":"Does Deep Learning Learn to Abstract? A Systematic Probing Framework","created":"2023-02-23","cited_by_count":6,"area":null},{"id":"2305.08208","title":"Learning to Generalize for Cross-domain QA","created":"2023-05-14","cited_by_count":6,"area":null},{"id":"2104.07571","title":"Toward Deconfounding the Influence of Entity Demographics for Question Answering Accuracy","created":"2021-04-15","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":"2404.17194","title":"TIGQA:An Expert Annotated Question Answering Dataset in Tigrinya","created":"2024-04-26","cited_by_count":5,"area":null},{"id":"2205.10661","title":"An Empirical Investigation of Commonsense Self-Supervision with Knowledge Graphs","created":"2022-05-21","cited_by_count":4,"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":"2210.13778","title":"IDK-MRC: Unanswerable Questions for Indonesian Machine Reading Comprehension","created":"2022-10-25","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":"2406.16779","title":"It Is Not About What You Say, It Is About How You Say It: A Surprisingly Simple Approach for Improving Reading Comprehension","created":"2024-06-24","cited_by_count":4,"area":null},{"id":"2107.08582","title":"Bridging the Gap between Language Model and Reading Comprehension: Unsupervised MRC via Self-Supervision","created":"2021-07-19","cited_by_count":3,"area":null},{"id":"2203.03208","title":"Trajectory Test-Train Overlap in Next-Location Prediction Datasets","created":"2022-03-07","cited_by_count":3,"area":null},{"id":"2107.00368","title":"Ensemble Learning-Based Approach for Improving Generalization Capability of Machine Reading Comprehension Systems","created":"2021-07-01","cited_by_count":2,"area":null},{"id":"2109.00077","title":"Interactive Machine Comprehension with Dynamic Knowledge Graphs","created":"2021-08-31","cited_by_count":2,"area":null},{"id":"2109.07102","title":"Can Edge Probing Tasks Reveal Linguistic Knowledge in QA Models?","created":"2021-09-15","cited_by_count":2,"area":null},{"id":"2204.04534","title":"Extending the Scope of Out-of-Domain: Examining QA models in multiple subdomains","created":"2022-04-09","cited_by_count":2,"area":null},{"id":"2204.08880","title":"Antipatterns in Software Classification Taxonomies","created":"2022-04-19","cited_by_count":1,"area":null},{"id":"2309.10945","title":"Benchmarks for Pir\\'a 2.0, a Reading Comprehension Dataset about the Ocean, the Brazilian Coast, and Climate Change","created":"2023-09-19","cited_by_count":1,"area":null},{"id":"2310.13856","title":"Implications of Annotation Artifacts in Edge Probing Test Datasets","created":"2023-10-20","cited_by_count":1,"area":null},{"id":"2402.10527","title":"Assessing biomedical knowledge robustness in large language models by query-efficient sampling attacks","created":"2024-02-16","cited_by_count":1,"area":null},{"id":"2509.05716","title":"A Survey of the State-of-the-Art in Conversational Question Answering Systems","created":"2025-09-06","cited_by_count":1,"area":null},{"id":"2112.00245","title":"True or False: Does the Deep Learning Model Learn to Detect Rumors?","created":"2021-12-01","cited_by_count":0,"area":null},{"id":"2112.03007","title":"How to Build Robust FAQ Chatbot with Controllable Question Generator?","created":"2021-11-18","cited_by_count":0,"area":null},{"id":"2202.11865","title":"Using calibrator to improve robustness in Machine Reading Comprehension","created":"2022-02-24","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":"2211.16093","title":"Penalizing Confident Predictions on Largely Perturbed Inputs Does Not Improve Out-of-Distribution Generalization in Question Answering","created":"2022-11-29","cited_by_count":0,"area":null},{"id":"2309.05103","title":"AGent: A Novel Pipeline for Automatically Creating Unanswerable Questions","created":"2023-09-10","cited_by_count":0,"area":null},{"id":"2512.00323","title":"Comparative Analysis of 47 Context-Based Question Answer Models Across 8 Diverse Datasets","created":"2025-11-29","cited_by_count":0,"area":null}],"next_cursor":null}