{"total":81,"rows":[{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916,"area":null},{"id":"2104.06039","title":"MultiModalQA: Complex Question Answering over Text, Tables and Images","created":"2021-04-13","cited_by_count":179,"area":null},{"id":"2103.06332","title":"Hurdles to Progress in Long-form Question Answering","created":"2021-03-10","cited_by_count":167,"area":null},{"id":"2210.11369","title":"On Feature Learning in the Presence of Spurious Correlations","created":"2022-10-20","cited_by_count":145,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2206.01347","title":"MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data","created":"2022-06-03","cited_by_count":121,"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":"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":"2402.12483","title":"Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question?","created":"2024-02-19","cited_by_count":71,"area":null},{"id":"2202.06856","title":"Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization","created":"2022-02-14","cited_by_count":69,"area":null},{"id":"2207.14251","title":"Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions","created":"2022-07-28","cited_by_count":57,"area":null},{"id":"2106.06052","title":"Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking","created":"2021-05-21","cited_by_count":53,"area":null},{"id":"2101.00133","title":"NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned","created":"2021-01-01","cited_by_count":52,"area":null},{"id":"2106.05469","title":"Variational Information Bottleneck for Effective Low-Resource Fine-Tuning","created":"2021-06-10","cited_by_count":51,"area":null},{"id":"2309.02706","title":"HAE-RAE Bench: Evaluation of Korean Knowledge in Language Models","created":"2023-09-06","cited_by_count":47,"area":null},{"id":"2110.07803","title":"Attacking Open-domain Question Answering by Injecting Misinformation","created":"2021-10-15","cited_by_count":41,"area":null},{"id":"2106.00969","title":"COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences","created":"2021-06-02","cited_by_count":40,"area":null},{"id":"2106.01024","title":"Why Machine Reading Comprehension Models Learn Shortcuts?","created":"2021-06-02","cited_by_count":40,"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":"2104.08161","title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","created":"2021-04-16","cited_by_count":32,"area":null},{"id":"2106.00872","title":"On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study","created":"2021-06-02","cited_by_count":31,"area":null},{"id":"2109.01156","title":"Challenges in Generalization in Open Domain Question Answering","created":"2021-09-02","cited_by_count":30,"area":null},{"id":"2212.10534","title":"DISCO: Distilling Counterfactuals with Large Language Models","created":"2022-12-20","cited_by_count":30,"area":null},{"id":"2104.10343","title":"Sensitivity as a Complexity Measure for Sequence Classification Tasks","created":"2021-04-21","cited_by_count":28,"area":null},{"id":"2305.09022","title":"It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance","created":"2023-05-15","cited_by_count":26,"area":null},{"id":"2305.04990","title":"Explanation-based Finetuning Makes Models More Robust to Spurious Cues","created":"2023-05-08","cited_by_count":25,"area":null},{"id":"2106.00794","title":"What Ingredients Make for an Effective Crowdsourcing Protocol for Difficult NLU Data Collection Tasks?","created":"2021-06-01","cited_by_count":23,"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":"2305.08414","title":"What's the Meaning of Superhuman Performance in Today's NLU?","created":"2023-05-15","cited_by_count":23,"area":null},{"id":"2110.04374","title":"A Few More Examples May Be Worth Billions of Parameters","created":"2021-10-08","cited_by_count":19,"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":"2203.06498","title":"The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning","created":"2022-03-12","cited_by_count":17,"area":null},{"id":"2111.04104","title":"Uncertainty Calibration for Ensemble-Based Debiasing Methods","created":"2021-11-07","cited_by_count":16,"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":"2109.10604","title":"NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset","created":"2021-09-22","cited_by_count":14,"area":null},{"id":"2205.12593","title":"Less Learn Shortcut: Analyzing and Mitigating Learning of Spurious Feature-Label Correlation","created":"2022-05-25","cited_by_count":13,"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":"2109.11314","title":"ParaShoot: A Hebrew Question Answering Dataset","created":"2021-09-23","cited_by_count":12,"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":"2203.06342","title":"What Makes Reading Comprehension Questions Difficult?","created":"2022-03-12","cited_by_count":11,"area":null},{"id":"2212.05421","title":"Feature-Level Debiased Natural Language Understanding","created":"2022-12-11","cited_by_count":10,"area":null},{"id":"2305.00581","title":"Multimodal Graph Transformer for Multimodal Question Answering","created":"2023-04-30","cited_by_count":10,"area":null},{"id":"2109.12085","title":"Text-based NP Enrichment","created":"2021-09-24","cited_by_count":8,"area":null},{"id":"2112.00086","title":"Dyna-bAbI: unlocking bAbI's potential with dynamic synthetic benchmarking","created":"2021-11-30","cited_by_count":7,"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":"2105.14668","title":"On the Interplay Between Fine-tuning and Composition in Transformers","created":"2021-05-31","cited_by_count":6,"area":null},{"id":"2205.12181","title":"Partial-input baselines show that NLI models can ignore context, but they don't","created":"2022-05-24","cited_by_count":6,"area":null},{"id":"2211.07040","title":"World Knowledge in Multiple Choice Reading Comprehension","created":"2022-11-13","cited_by_count":6,"area":null},{"id":"2211.07950","title":"Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs","created":"2022-11-15","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":"2106.03831","title":"Counterfactual Maximum Likelihood Estimation for Training Deep Networks","created":"2021-06-07","cited_by_count":5,"area":null},{"id":"2305.18917","title":"Fighting Bias with Bias: Promoting Model Robustness by Amplifying Dataset Biases","created":"2023-05-30","cited_by_count":5,"area":null},{"id":"2105.10334","title":"Fact-driven Logical Reasoning for Machine Reading Comprehension","created":"2021-05-21","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":"2210.13439","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":"2307.01076","title":"Analyzing Multiple-Choice Reading and Listening Comprehension Tests","created":"2023-07-03","cited_by_count":4,"area":null},{"id":"2108.14006","title":"A Generative Approach for Mitigating Structural Biases in Natural Language Inference","created":"2021-08-31","cited_by_count":3,"area":null},{"id":"2203.10693","title":"Leveraging Expert Guided Adversarial Augmentation For Improving Generalization in Named Entity Recognition","created":"2022-03-21","cited_by_count":3,"area":null},{"id":"2502.06316","title":"Can AI Examine Novelty of Patents?: Novelty Evaluation Based on the Correspondence between Patent Claim and Prior Art","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2102.03016","title":"Model Agnostic Answer Reranking System for Adversarial Question Answering","created":"2021-02-05","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":"2203.06404","title":"A Proposal to Study \"Is High Quality Data All We Need?\"","created":"2022-03-12","cited_by_count":2,"area":null},{"id":"2103.14443","title":"Incorporating Connections Beyond Knowledge Embeddings: A Plug-and-Play Module to Enhance Commonsense Reasoning in Machine Reading Comprehension","created":"2021-03-26","cited_by_count":1,"area":null},{"id":"2110.11899","title":"Challenges in Procedural Multimodal Machine Comprehension:A Novel Way To Benchmark","created":"2021-10-22","cited_by_count":1,"area":null},{"id":"2210.07566","title":"A Survey of Parameters Associated with the Quality of Benchmarks in NLP","created":"2022-10-14","cited_by_count":1,"area":null},{"id":"2210.07631","title":"Hardness of Samples Need to be Quantified for a Reliable Evaluation System: Exploring Potential Opportunities with a New Task","created":"2022-10-14","cited_by_count":1,"area":null},{"id":"2303.02846","title":"Contrastive variational information bottleneck for aspect-based sentiment analysis","created":"2023-03-06","cited_by_count":1,"area":null},{"id":"2305.04737","title":"SkillQG: Learning to Generate Question for Reading Comprehension Assessment","created":"2023-05-08","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":"2401.17498","title":"Improving QA Model Performance with Cartographic Inoculation","created":"2024-01-30","cited_by_count":1,"area":null},{"id":"2402.19076","title":"Pointing out the Shortcomings of Relation Extraction Models with Semantically Motivated Adversarials","created":"2024-02-29","cited_by_count":1,"area":null},{"id":"2503.05047","title":"Biases in Large Language Model-Elicited Text: A Case Study in Natural Language Inference","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2506.14587","title":"SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust Classification","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2207.08943","title":"MRCLens: an MRC Dataset Bias Detection Toolkit","created":"2022-07-18","cited_by_count":0,"area":null},{"id":"2212.11670","title":"Evaluation for Change","created":"2022-12-20","cited_by_count":0,"area":null},{"id":"2302.04434","title":"Real-Time Visual Feedback to Guide Benchmark Creation: A Human-and-Metric-in-the-Loop Workflow","created":"2023-02-09","cited_by_count":0,"area":null},{"id":"2311.09605","title":"Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2410.08996","title":"Hypothesis-only Biases in Large Language Model-Elicited Natural Language Inference","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2609.24885","title":"The Copy Ceiling: An Input-Exposure Control for Ontology-Grounded Generation over Curated Corpora","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.17747","title":"Auditing Failure Attribution: Label Predictability and Judge Behavior","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}