{"total":71,"rows":[{"id":"2102.01951","title":"Mind the Gap: Assessing Temporal Generalization in Neural Language Models","created":"2021-02-03","cited_by_count":230,"area":null},{"id":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155,"area":null},{"id":"2202.07206","title":"Impact of Pretraining Term Frequencies on Few-Shot Reasoning","created":"2022-02-15","cited_by_count":142,"area":"lr"},{"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":"2109.00904","title":"MultiEURLEX -- A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer","created":"2021-09-02","cited_by_count":90,"area":null},{"id":"2311.17295","title":"Elo Uncovered: Robustness and Best Practices in Language Model Evaluation","created":"2023-11-29","cited_by_count":61,"area":null},{"id":"2110.00806","title":"Swiss-Judgment-Prediction: A Multilingual Legal Judgment Prediction Benchmark","created":"2021-10-02","cited_by_count":60,"area":null},{"id":"2106.11872","title":"Randomness In Neural Network Training: Characterizing The Impact of Tooling","created":"2021-06-22","cited_by_count":59,"area":null},{"id":"2203.07228","title":"FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processing","created":"2022-03-14","cited_by_count":49,"area":null},{"id":"2110.03036","title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","created":"2021-10-06","cited_by_count":47,"area":null},{"id":"2111.12790","title":"Temporal Effects on Pre-trained Models for Language Processing Tasks","created":"2021-11-24","cited_by_count":46,"area":null},{"id":"2109.07276","title":"Sequence Length is a Domain: Length-based Overfitting in Transformer Models","created":"2021-09-15","cited_by_count":35,"area":null},{"id":"2105.02590","title":"Reliability Testing for Natural Language Processing Systems","created":"2021-05-06","cited_by_count":25,"area":null},{"id":"2203.07856","title":"Improved Multi-label Classification under Temporal Concept Drift: Rethinking Group-Robust Algorithms in a Label-Wise Setting","created":"2022-03-15","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":"2302.12297","title":"Dynamic Benchmarking of Masked Language Models on Temporal Concept Drift with Multiple Views","created":"2023-02-23","cited_by_count":21,"area":null},{"id":"2108.05682","title":"(Un)solving Morphological Inflection: Lemma Overlap Artificially Inflates Models' Performance","created":"2021-08-12","cited_by_count":20,"area":null},{"id":"2106.00473","title":"SemEval-2021 Task 1: Lexical Complexity Prediction","created":"2021-06-01","cited_by_count":19,"area":null},{"id":"2106.09069","title":"Automatic Construction of Evaluation Suites for Natural Language Generation Datasets","created":"2021-06-16","cited_by_count":18,"area":null},{"id":"2111.06467","title":"SynthBio: A Case Study in Human-AI Collaborative Curation of Text Datasets","created":"2021-11-11","cited_by_count":18,"area":null},{"id":"2204.13516","title":"What do You Mean by Relation Extraction? A Survey on Datasets and Study on Scientific Relation Classification","created":"2022-04-28","cited_by_count":17,"area":null},{"id":"2302.03147","title":"It's about Time: Rethinking Evaluation on Rumor Detection Benchmarks using Chronological Splits","created":"2023-02-06","cited_by_count":15,"area":null},{"id":"2310.15757","title":"Do Differences in Values Influence Disagreements in Online Discussions?","created":"2023-10-24","cited_by_count":15,"area":null},{"id":"2210.09197","title":"On the Impact of Temporal Concept Drift on Model Explanations","created":"2022-10-17","cited_by_count":14,"area":null},{"id":"2210.07931","title":"Sequential Learning Of Neural Networks for Prequential MDL","created":"2022-10-14","cited_by_count":13,"area":null},{"id":"2204.09391","title":"You Are What You Write: Preserving Privacy in the Era of Large Language Models","created":"2022-04-20","cited_by_count":12,"area":null},{"id":"2106.15065","title":"Rethinking End-to-End Evaluation of Decomposable Tasks: A Case Study on Spoken Language Understanding","created":"2021-06-29","cited_by_count":11,"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":"2405.14211","title":"ChronosLex: Time-aware Incremental Training for Temporal Generalization of Legal Classification Tasks","created":"2024-05-23","cited_by_count":11,"area":null},{"id":"2204.06251","title":"Experimental Standards for Deep Learning in Natural Language Processing Research","created":"2022-04-13","cited_by_count":10,"area":null},{"id":"2205.00034","title":"What do we Really Know about State of the Art NER?","created":"2022-04-29","cited_by_count":10,"area":null},{"id":"2210.06799","title":"Benchmarking Long-tail Generalization with Likelihood Splits","created":"2022-10-13","cited_by_count":9,"area":null},{"id":"2305.13342","title":"On the Limitations of Simulating Active Learning","created":"2023-05-21","cited_by_count":9,"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":"2208.12888","title":"Investigating data partitioning strategies for crosslinguistic low-resource ASR evaluation","created":"2022-08-26","cited_by_count":7,"area":null},{"id":"2506.06313","title":"Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering","created":"2025-05-26","cited_by_count":7,"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":"2306.12550","title":"On Evaluation of Document Classification using RVL-CDIP","created":"2023-06-21","cited_by_count":5,"area":null},{"id":"2402.14482","title":"SpanSeq: Similarity-based sequence data splitting method for improved development and assessment of deep learning projects","created":"2024-02-22","cited_by_count":5,"area":null},{"id":"2403.00252","title":"EUROPA: A Legal Multilingual Keyphrase Generation Dataset","created":"2024-03-01","cited_by_count":5,"area":null},{"id":"2403.20056","title":"Cross-Lingual Transfer Robustness to Lower-Resource Languages on Adversarial Datasets","created":"2024-03-29","cited_by_count":5,"area":null},{"id":"2404.08354","title":"PMB5: Gaining More Insight into Neural Semantic Parsing with Challenging Benchmarks","created":"2024-04-12","cited_by_count":5,"area":null},{"id":"2302.04054","title":"Towards Inferential Reproducibility of Machine Learning Research","created":"2023-02-08","cited_by_count":4,"area":null},{"id":"2210.13628","title":"Predicting Long-Term Citations from Short-Term Linguistic Influence","created":"2022-10-24","cited_by_count":3,"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":"2210.12392","title":"Testing Independence of Exchangeable Random Variables","created":"2022-10-22","cited_by_count":2,"area":null},{"id":"2309.11576","title":"Examining the Limitations of Computational Rumor Detection Models Trained on Static Datasets","created":"2023-09-20","cited_by_count":2,"area":null},{"id":"2312.03886","title":"On The Fairness Impacts of Hardware Selection in Machine Learning","created":"2023-12-06","cited_by_count":2,"area":null},{"id":"2505.21816","title":"Revisiting Common Assumptions about Arabic Dialects in NLP","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2109.08597","title":"Boosting Transformers for Job Expression Extraction and Classification in a Low-Resource Setting","created":"2021-09-17","cited_by_count":1,"area":null},{"id":"2311.08249","title":"On Using Distribution-Based Compositionality Assessment to Evaluate Compositional Generalisation in Machine Translation","created":"2023-11-14","cited_by_count":1,"area":null},{"id":"2402.12627","title":"A Comprehensive Review of Machine Learning Advances on Data Change: A Cross-Field Perspective","created":"2024-02-20","cited_by_count":1,"area":null},{"id":"2404.09371","title":"The Effect of Data Partitioning Strategy on Model Generalizability: A Case Study of Morphological Segmentation","created":"2024-04-14","cited_by_count":1,"area":null},{"id":"2410.13460","title":"From Citations to Criticality: Predicting Legal Decision Influence in the Multilingual Swiss Jurisprudence","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2509.22612","title":"Beyond statistical significance: Quantifying uncertainty and statistical variability in multilingual and multitask NLP evaluation","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2606.15959","title":"Quantifying the Impact of Lossy Compression on Neural Generative Surrogate Modeling","created":"2026-06-14","cited_by_count":1,"area":null},{"id":"2207.04003","title":"No Time Like the Present: Effects of Language Change on Automated Comment Moderation","created":"2022-07-08","cited_by_count":0,"area":null},{"id":"2209.06699","title":"The Fragility of Multi-Treebank Parsing Evaluation","created":"2022-09-14","cited_by_count":0,"area":null},{"id":"2209.07139","title":"The Impact of Edge Displacement Vaserstein Distance on UD Parsing Performance","created":"2022-09-15","cited_by_count":0,"area":null},{"id":"2311.10236","title":"Latent Feature-based Data Splits to Improve Generalisation Evaluation: A Hate Speech Detection Case Study","created":"2023-11-16","cited_by_count":0,"area":"safety"},{"id":"2405.19461","title":"Clustering-Based Validation Splits for Model Selection under Domain Shift","created":"2024-05-29","cited_by_count":0,"area":null},{"id":"2407.04010","title":"Exploring Diachronic and Diatopic Changes in Dialect Continua: Tasks, Datasets and Challenges","created":"2024-07-04","cited_by_count":0,"area":null},{"id":"2410.13802","title":"Adversarial Testing as a Tool for Interpretability: Length-based Overfitting of Elementary Functions in Transformers","created":"2024-10-17","cited_by_count":0,"area":null},{"id":"2511.11773","title":"On the Measure of a Model: From Intelligence to Generality","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2602.12759","title":"Towards a Diagnostic and Predictive Evaluation Methodology for Sequence Labeling Tasks","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2603.22977","title":"DariMis: Harm-Aware Modeling for Dari Misinformation Detection on YouTube","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2604.16392","title":"RoMathExam: A Longitudinal Dataset of Romanian Math Exams (1895-2025) with a Seven-Decade Core (1957-2025)","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2606.27808","title":"Learning Complementary Action Modeling from Automotive Maintenance Instructions","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.19718","title":"Lightweight Person-Place Relation Extraction from Historical Newspapers with Dependency Graphs and Proximity Features","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.17223","title":"Temporal Leakage in Financial News NLP: A Multi-Architecture Audit with a Regime-Specific M&A Signal","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2610.12694","title":"Critical Mass: Structure-Disjoint Splits Drift With the Libraries They Are Built On","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}