{"total":70,"rows":[{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807,"area":null},{"id":"2103.03098","title":"Accounting for Variance in Machine Learning Benchmarks","created":"2021-03-01","cited_by_count":201,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"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":"2205.06009","title":"Falsesum: Generating Document-level NLI Examples for Recognizing Factual Inconsistency in Summarization","created":"2022-05-12","cited_by_count":34,"area":null},{"id":"2204.07610","title":"Sources of Irreproducibility in Machine Learning: A Review","created":"2022-04-15","cited_by_count":32,"area":null},{"id":"2212.02974","title":"CySecBERT: A Domain-Adapted Language Model for the Cybersecurity Domain","created":"2022-12-06","cited_by_count":31,"area":null},{"id":"2106.05532","title":"How Robust are Model Rankings: A Leaderboard Customization Approach for Equitable Evaluation","created":"2021-06-10","cited_by_count":24,"area":null},{"id":"2109.03160","title":"How much pretraining data do language models need to learn syntax?","created":"2021-09-07","cited_by_count":21,"area":null},{"id":"2204.04026","title":"Fair and Argumentative Language Modeling for Computational Argumentation","created":"2022-04-08","cited_by_count":18,"area":null},{"id":"2307.10214","title":"Time for aCTIon: Automated Analysis of Cyber Threat Intelligence in the Wild","created":"2023-07-14","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":"2210.13393","title":"We need to talk about random seeds","created":"2022-10-24","cited_by_count":13,"area":null},{"id":"2402.12801","title":"Few-shot clinical entity recognition in English, French and Spanish: masked language models outperform generative model prompting","created":"2024-02-20","cited_by_count":12,"area":null},{"id":"2102.06008","title":"Cross-Domain Multi-Task Learning for Sequential Sentence Classification in Research Papers","created":"2021-02-11","cited_by_count":11,"area":null},{"id":"2206.05985","title":"Modeling the Machine Learning Multiverse","created":"2022-06-13","cited_by_count":11,"area":null},{"id":"2609.27678","title":"Same Scores, Different Decisions: Evaluating JEV and Language Models for Legal Document Understanding","created":"2026-09-23","cited_by_count":11,"area":null},{"id":"2207.12571","title":"Innovations in Neural Data-to-text Generation: A Survey","created":"2022-07-25","cited_by_count":10,"area":null},{"id":"2104.08878","title":"Perspectives on Machine Learning from Psychology's Reproducibility Crisis","created":"2021-04-18","cited_by_count":9,"area":null},{"id":"2212.09747","title":"Do CoNLL-2003 Named Entity Taggers Still Work Well in 2023?","created":"2022-12-19","cited_by_count":9,"area":null},{"id":"2102.08858","title":"Metrical Tagging in the Wild: Building and Annotating Poetry Corpora with Rhythmic Features","created":"2021-02-17","cited_by_count":8,"area":null},{"id":"2107.14154","title":"SeqScore: Addressing Barriers to Reproducible Named Entity Recognition Evaluation","created":"2021-07-29","cited_by_count":8,"area":null},{"id":"2108.07556","title":"Not All Linearizations Are Equally Data-Hungry in Sequence Labeling Parsing","created":"2021-08-17","cited_by_count":7,"area":null},{"id":"2312.00100","title":"Introducing Rhetorical Parallelism Detection: A New Task with Datasets, Metrics, and Baselines","created":"2023-11-30","cited_by_count":7,"area":null},{"id":"2511.19794","title":"When +1% Is Not Enough: A Paired Bootstrap Protocol for Evaluating Small Improvements","created":"2025-11-24","cited_by_count":7,"area":null},{"id":"2102.12227","title":"Multi-Task Attentive Residual Networks for Argument Mining","created":"2021-02-24","cited_by_count":6,"area":null},{"id":"2106.07343","title":"Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling","created":"2021-05-25","cited_by_count":6,"area":null},{"id":"2110.00613","title":"Expected Validation Performance and Estimation of a Random Variable's Maximum","created":"2021-10-01","cited_by_count":6,"area":null},{"id":"2203.12881","title":"Can Unsupervised Knowledge Transfer from Social Discussions Help Argument Mining?","created":"2022-03-24","cited_by_count":5,"area":null},{"id":"2211.04256","title":"Bridging Fairness and Environmental Sustainability in Natural Language Processing","created":"2022-11-08","cited_by_count":5,"area":null},{"id":"2202.13610","title":"Did AI get more negative recently?","created":"2022-02-28","cited_by_count":4,"area":null},{"id":"2302.04054","title":"Towards Inferential Reproducibility of Machine Learning Research","created":"2023-02-08","cited_by_count":4,"area":null},{"id":"2309.08316","title":"How to Handle Different Types of Out-of-Distribution Scenarios in Computational Argumentation? A Comprehensive and Fine-Grained Field Study","created":"2023-09-15","cited_by_count":4,"area":null},{"id":"2501.11770","title":"The Value of Nothing: Multimodal Extraction of Human Values Expressed by TikTok Influencers","created":"2025-01-20","cited_by_count":4,"area":null},{"id":"2108.06896","title":"Challenges for cognitive decoding using deep learning methods","created":"2021-08-16","cited_by_count":3,"area":null},{"id":"2111.01562","title":"Evaluating deep transfer learning for whole-brain cognitive decoding","created":"2021-11-01","cited_by_count":3,"area":null},{"id":"2501.14809","title":"Evaluation of Seismic Artificial Intelligence with Uncertainty","created":"2025-01-15","cited_by_count":3,"area":null},{"id":"2510.06730","title":"PTEB: Towards Robust Text Embedding Evaluation via Stochastic Paraphrasing at Evaluation Time with LLMs","created":"2025-10-08","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":"2208.01099","title":"Parsimonious Argument Annotations for Hate Speech Counter-narratives","created":"2022-08-01","cited_by_count":2,"area":null},{"id":"2310.00679","title":"CebuaNER: A New Baseline Cebuano Named Entity Recognition Model","created":"2023-10-01","cited_by_count":2,"area":null},{"id":"2312.13495","title":"Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2409.15202","title":"ASTE Transformer Modelling Dependencies in Aspect-Sentiment Triplet Extraction","created":"2024-09-23","cited_by_count":2,"area":null},{"id":"2506.06808","title":"Not quite Sherlock Holmes: Language model predictions do not reliably differentiate impossible from improbable events","created":"2025-06-07","cited_by_count":2,"area":null},{"id":"2110.05892","title":"Investigation on Data Adaptation Techniques for Neural Named Entity Recognition","created":"2021-10-12","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":"2406.08307","title":"Measuring training variability from stochastic optimization using robust nonparametric testing","created":"2024-06-12","cited_by_count":1,"area":null},{"id":"2503.04405","title":"Comparative Study of Zero-Shot Cross-Lingual Transfer for Bodo POS and NER Tagging Using Gemini 2.0 Flash Thinking Experimental Model","created":"2025-03-06","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":"2605.20043","title":"Mind Your Moras: Orthography-Aware Error Analysis of Neural Japanese Morphological Generation","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2605.28190","title":"The Harder Text Embedding Benchmark (HTEB): Beyond One-dimensional Static Robustness","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2606.24381","title":"On the Stability of Prompt Ranking in Large Language Model Evaluation","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2609.04871","title":"AutoLR: Automating the Path from Research to Launch Review in Industrial Recommender Systems","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2101.09079","title":"Evaluation Discrepancy Discovery: A Sentence Compression Case-study","created":"2021-01-22","cited_by_count":0,"area":null},{"id":"2109.13611","title":"Active Learning for Argument Mining: A Practical Approach","created":"2021-09-28","cited_by_count":0,"area":null},{"id":"2309.05668","title":"Studying the impacts of pre-training using ChatGPT-generated text on downstream tasks","created":"2023-09-02","cited_by_count":0,"area":null},{"id":"2311.05075","title":"Mental Health Diagnosis in the Digital Age: Harnessing Sentiment Analysis on Social Media Platforms upon Ultra-Sparse Feature Content","created":"2023-11-09","cited_by_count":0,"area":null},{"id":"2311.09930","title":"A Framework for Monitoring and Retraining Language Models in Real-World Applications","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2503.05373","title":"Leveraging Semantic Type Dependencies for Clinical Named Entity Recognition","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2606.19638","title":"MiqraBERT: Regression-Based Sentence-BERT Finetuning for Biblical Hebrew Parallel Detection","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2608.01454","title":"How Benchmarks and Evaluation Protocols Shape Conclusions in Provenance-Based Intrusion Detection","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.13329","title":"A Probe Direction Is a Property of Its Prompt","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.30895","title":"A Controlled Evaluation of Model Rankings and Input Reliance in Surface Water Segmentation","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.07766","title":"Bag of Tricks or Bag of Myths? Reducing Modeling Complexity with Task Knowledge in Explainable Suicide Risk Assessment","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.15122","title":"DepthBenchCAD: When Does Deeper Auditing Yield More Reliable Conclusions?","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.21179","title":"Not All Irregularity Is Equal: Causally Isolating a Rare Failure Mode in Japanese Morphological Inflection","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.25006","title":"What Does 99% Accuracy Measure? A Reproducible Audit of Shortcut Learning in a Widely Used Fake News Corpus","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2609.25152","title":"Exposing Blind Spots in Deep Imbalanced Regression Evaluation","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.16825","title":"Mean Accuracy Is the Wrong Estimand for a Release Decision","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.20279","title":"Neural POS Tagging for the Low-Resource Saraiki","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}