{"total":22,"rows":[{"id":"2308.01263","title":"XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models","created":"2023-08-02","cited_by_count":505,"area":null},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459,"area":null},{"id":"2107.04649","title":"Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization","created":"2021-07-09","cited_by_count":249,"area":null},{"id":"2106.16163","title":"The MultiBERTs: BERT Reproductions for Robustness Analysis","created":"2021-06-30","cited_by_count":92,"area":null},{"id":"2205.12411","title":"Linear Connectivity Reveals Generalization Strategies","created":"2022-05-24","cited_by_count":56,"area":null},{"id":"2108.05921","title":"Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-based Hate","created":"2021-08-12","cited_by_count":50,"area":null},{"id":"2202.05834","title":"Predicting Out-of-Distribution Error with the Projection Norm","created":"2022-02-11","cited_by_count":50,"area":null},{"id":"2110.08300","title":"The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail","created":"2021-10-15","cited_by_count":38,"area":null},{"id":"2203.03073","title":"ILDAE: Instance-Level Difficulty Analysis of Evaluation Data","created":"2022-03-07","cited_by_count":17,"area":null},{"id":"2205.00328","title":"HateCheckHIn: Evaluating Hindi Hate Speech Detection Models","created":"2022-04-30","cited_by_count":15,"area":null},{"id":"2312.01082","title":"A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomness","created":"2023-12-02","cited_by_count":14,"area":null},{"id":"2412.04619","title":"Sometimes I am a Tree: Data Drives Unstable Hierarchical Generalization","created":"2024-12-05","cited_by_count":10,"area":null},{"id":"2205.09460","title":"Why only Micro-F1? Class Weighting of Measures for Relation Classification","created":"2022-05-19","cited_by_count":8,"area":null},{"id":"2502.17356","title":"Random Scaling of Emergent Capabilities","created":"2025-02-24","cited_by_count":7,"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":"2402.08382","title":"Punctuation Restoration Improves Structure Understanding Without Supervision","created":"2024-02-13","cited_by_count":3,"area":null},{"id":"2111.04824","title":"MassFormer: Tandem Mass Spectrum Prediction for Small Molecules using Graph Transformers","created":"2021-11-08","cited_by_count":2,"area":null},{"id":"2201.01845","title":"Data-driven Model Generalizability in Crosslinguistic Low-resource Morphological Segmentation","created":"2022-01-05","cited_by_count":2,"area":null},{"id":"2204.08102","title":"kpfriends at SemEval-2022 Task 2: NEAMER -- Named Entity Augmented Multi-word Expression Recognizer","created":"2022-04-17","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":"2402.12817","title":"On Sensitivity of Learning with Limited Labelled Data to the Effects of Randomness: Impact of Interactions and Systematic Choices","created":"2024-02-20","cited_by_count":1,"area":null},{"id":"2506.14613","title":"When Does Meaning Backfire? Investigating the Role of AMRs in NLI","created":"2025-06-17","cited_by_count":1,"area":null}],"next_cursor":null}