{"total":89,"rows":[{"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":"2103.08493","title":"How Many Data Points is a Prompt Worth?","created":"2021-03-15","cited_by_count":198,"area":null},{"id":"2204.07580","title":"mGPT: Few-Shot Learners Go Multilingual","created":"2022-04-15","cited_by_count":142,"area":null},{"id":"2305.06329","title":"Similarity of Neural Network Models: A Survey of Functional and Representational Measures","created":"2023-05-10","cited_by_count":131,"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":"2106.16163","title":"The MultiBERTs: BERT Reproductions for Robustness Analysis","created":"2021-06-30","cited_by_count":92,"area":null},{"id":"2302.07011","title":"A Modern Look at the Relationship between Sharpness and Generalization","created":"2023-02-14","cited_by_count":92,"area":null},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2110.01518","title":"Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics","created":"2021-10-04","cited_by_count":67,"area":null},{"id":"2205.12411","title":"Linear Connectivity Reveals Generalization Strategies","created":"2022-05-24","cited_by_count":56,"area":null},{"id":"2209.00613","title":"ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets","created":"2022-09-01","cited_by_count":44,"area":null},{"id":"2106.08694","title":"On the proper role of linguistically-oriented deep net analysis in linguistic theorizing","created":"2021-06-16","cited_by_count":43,"area":null},{"id":"2305.14701","title":"Modeling rapid language learning by distilling Bayesian priors into artificial neural networks","created":"2023-05-24","cited_by_count":42,"area":null},{"id":"2502.19249","title":"Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases","created":"2025-02-26","cited_by_count":37,"area":null},{"id":"2109.06096","title":"The Grammar-Learning Trajectories of Neural Language Models","created":"2021-09-13","cited_by_count":36,"area":null},{"id":"2406.14479","title":"Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity","created":"2024-06-20","cited_by_count":36,"area":null},{"id":"2503.09543","title":"PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs","created":"2025-03-12","cited_by_count":35,"area":null},{"id":"2105.06020","title":"Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level","created":"2021-05-13","cited_by_count":34,"area":null},{"id":"2503.02854","title":"(How) Do Language Models Track State?","created":"2025-03-04","cited_by_count":34,"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":"2108.01661","title":"Grounding Representation Similarity with Statistical Testing","created":"2021-08-03","cited_by_count":29,"area":null},{"id":"2307.04138","title":"On The Impact of Machine Learning Randomness on Group Fairness","created":"2023-07-09","cited_by_count":26,"area":null},{"id":"2211.00107","title":"Where to start? Analyzing the potential value of intermediate models","created":"2022-10-31","cited_by_count":23,"area":null},{"id":"2308.07120","title":"Position: Key Claims in LLM Research Have a Long Tail of Footnotes","created":"2023-08-14","cited_by_count":20,"area":null},{"id":"2108.06743","title":"Exploring Generalization Ability of Pretrained Language Models on Arithmetic and Logical Reasoning","created":"2021-08-15","cited_by_count":17,"area":null},{"id":"2109.04095","title":"Debiasing Methods in Natural Language Understanding Make Bias More Accessible","created":"2021-09-09","cited_by_count":17,"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":"2210.06545","title":"GULP: a prediction-based metric between representations","created":"2022-10-12","cited_by_count":17,"area":null},{"id":"2501.14959","title":"Systemizing Multiplicity: The Curious Case of Arbitrariness in Machine Learning","created":"2025-01-24","cited_by_count":17,"area":null},{"id":"2104.10640","title":"The NLP Cookbook: Modern Recipes for Transformer based Deep Learning Architectures","created":"2021-03-23","cited_by_count":16,"area":null},{"id":"2308.09543","title":"Latent State Models of Training Dynamics","created":"2023-08-18","cited_by_count":16,"area":null},{"id":"2109.02102","title":"Teaching Autoregressive Language Models Complex Tasks By Demonstration","created":"2021-09-05","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":"2105.05641","title":"How Reliable are Model Diagnostics?","created":"2021-05-12","cited_by_count":13,"area":null},{"id":"2110.08419","title":"Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding","created":"2021-10-16","cited_by_count":12,"area":null},{"id":"2310.14993","title":"Understanding the Inner Workings of Language Models Through Representation Dissimilarity","created":"2023-10-23","cited_by_count":12,"area":null},{"id":"2403.03942","title":"The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models","created":"2024-03-06","cited_by_count":10,"area":null},{"id":"2210.12673","title":"Lexical Generalization Improves with Larger Models and Longer Training","created":"2022-10-23","cited_by_count":9,"area":null},{"id":"2102.10084","title":"Hate-Alert@DravidianLangTech-EACL2021: Ensembling strategies for Transformer-based Offensive language Detection","created":"2021-02-19","cited_by_count":8,"area":null},{"id":"2104.10105","title":"Neural Networks for Learning Counterfactual G-Invariances from Single Environments","created":"2021-04-20","cited_by_count":8,"area":null},{"id":"2507.06445","title":"Can Interpretation Predict Behavior on Unseen Data?","created":"2025-07-08","cited_by_count":8,"area":null},{"id":"2310.13191","title":"Towards Robust Pruning: An Adaptive Knowledge-Retention Pruning Strategy for Language Models","created":"2023-10-19","cited_by_count":7,"area":null},{"id":"2311.00863","title":"Training Dynamics of Contextual N-Grams in Language Models","created":"2023-11-01","cited_by_count":7,"area":null},{"id":"2405.17420","title":"Survival of the Fittest Representation: A Case Study with Modular Addition","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2502.17356","title":"Random Scaling of Emergent Capabilities","created":"2025-02-24","cited_by_count":7,"area":null},{"id":"2112.05364","title":"Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation","created":"2021-12-10","cited_by_count":6,"area":null},{"id":"2204.04735","title":"Reducing Model Jitter: Stable Re-training of Semantic Parsers in Production Environments","created":"2022-04-10","cited_by_count":6,"area":null},{"id":"2312.02730","title":"Towards Measuring Representational Similarity of Large Language Models","created":"2023-12-05","cited_by_count":6,"area":null},{"id":"2410.22660","title":"Linguistics Theory Meets LLM: Code-Switched Text Generation via Equivalence Constrained Large Language Models","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2111.09612","title":"How Emotionally Stable is ALBERT? Testing Robustness with Stochastic Weight Averaging on a Sentiment Analysis Task","created":"2021-11-18","cited_by_count":5,"area":null},{"id":"2211.11087","title":"Conceptor-Aided Debiasing of Large Language Models","created":"2022-11-20","cited_by_count":5,"area":null},{"id":"2505.05409","title":"Hide & Seek: Transformer Symmetries Obscure Sharpness & Riemannian Geometry Finds It","created":"2025-05-08","cited_by_count":5,"area":null},{"id":"2201.02734","title":"Building Human-like Communicative Intelligence: A Grounded Perspective","created":"2022-01-02","cited_by_count":4,"area":null},{"id":"2311.03663","title":"Principles from Clinical Research for NLP Model Generalization","created":"2023-11-07","cited_by_count":4,"area":null},{"id":"2406.19892","title":"Automatic register identification for the open web using multilingual deep learning","created":"2024-06-28","cited_by_count":4,"area":null},{"id":"2407.12220","title":"Questionable practices in machine learning","created":"2024-07-17","cited_by_count":4,"area":null},{"id":"2407.13070","title":"The Cost of Arbitrariness for Individuals: Examining the Legal and Technical Challenges of Model Multiplicity","created":"2024-05-28","cited_by_count":4,"area":null},{"id":"2505.20209","title":"Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data Selection","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2206.08446","title":"Methods for Estimating and Improving Robustness of Language Models","created":"2022-06-16","cited_by_count":3,"area":null},{"id":"2207.00560","title":"Is neural language acquisition similar to natural? A chronological probing study","created":"2022-07-01","cited_by_count":3,"area":null},{"id":"2210.12206","title":"Probing with Noise: Unpicking the Warp and Weft of Embeddings","created":"2022-10-21","cited_by_count":3,"area":null},{"id":"2301.11845","title":"Learning the Effects of Physical Actions in a Multi-modal Environment","created":"2023-01-27","cited_by_count":3,"area":null},{"id":"2305.12709","title":"Cross-lingual Transfer Can Worsen Bias in Sentiment Analysis","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2310.08008","title":"Effects of Human Adversarial and Affable Samples on BERT Generalization","created":"2023-10-12","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":"2402.17936","title":"Acquiring Linguistic Knowledge from Multimodal Input","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2406.02329","title":"On Affine Homotopy between Language Encoders","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2101.07632","title":"Situation and Behavior Understanding by Trope Detection on Films","created":"2021-01-19","cited_by_count":2,"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":"2201.02229","title":"Large-scale protein-protein post-translational modification extraction with distant supervision and confidence calibrated BioBERT","created":"2022-01-06","cited_by_count":2,"area":null},{"id":"2210.11589","title":"Monotonic Risk Relationships under Distribution Shifts for Regularized Risk Minimization","created":"2022-10-20","cited_by_count":2,"area":null},{"id":"2211.13331","title":"Using Focal Loss to Fight Shallow Heuristics: An Empirical Analysis of Modulated Cross-Entropy in Natural Language Inference","created":"2022-11-23","cited_by_count":2,"area":null},{"id":"2406.12471","title":"Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy Interpolation","created":"2024-06-18","cited_by_count":2,"area":null},{"id":"2409.06803","title":"Decomposition of surprisal: Unified computational model of ERP components in language processing","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2602.00977","title":"Trust in One Round: Confidence Estimation for Large Language Models via Structural Signals","created":"2026-02-01","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":"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":"2402.15925","title":"MultiContrievers: Analysis of Dense Retrieval Representations","created":"2024-02-24","cited_by_count":1,"area":null},{"id":"2408.05664","title":"Training an NLP Scholar at a Small Liberal Arts College: A Backwards Designed Course Proposal","created":"2024-08-11","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},{"id":"2108.13653","title":"Explaining Classes through Word Attribution","created":"2021-08-31","cited_by_count":0,"area":null},{"id":"2208.09669","title":"Lost in Context? On the Sense-wise Variance of Contextualized Word Embeddings","created":"2022-08-20","cited_by_count":0,"area":null},{"id":"2304.03145","title":"Evaluating the Robustness of Machine Reading Comprehension Models to Low Resource Entity Renaming","created":"2023-04-06","cited_by_count":0,"area":null},{"id":"2404.00069","title":"A Two-Phase Recall-and-Select Framework for Fast Model Selection","created":"2024-03-28","cited_by_count":0,"area":null},{"id":"2510.19427","title":"Revisiting the Relation Between Robustness and Universality","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2511.06234","title":"Analyzing and Mitigating Negation Artifacts using Data Augmentation for Improving ELECTRA-Small Model Accuracy","created":"2025-11-09","cited_by_count":0,"area":null},{"id":"2605.15901","title":"From Layers to Networks: Comparing Neural Representations via Diffusion Geometry","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2607.18305","title":"The Information Shadow: Measuring Structural Limits on What Language Models Can Learn","created":"2026-07-17","cited_by_count":0,"area":null}],"next_cursor":null}