{"total":22,"rows":[{"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":"2110.07732","title":"The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization","created":"2021-10-14","cited_by_count":62,"area":null},{"id":"2105.14802","title":"On Compositional Generalization of Neural Machine Translation","created":"2021-05-31","cited_by_count":34,"area":null},{"id":"2109.01135","title":"Sequence-to-Sequence Learning with Latent Neural Grammars","created":"2021-09-02","cited_by_count":30,"area":null},{"id":"2209.15342","title":"Emergent Communication: Generalization and Overfitting in Lewis Games","created":"2022-09-30","cited_by_count":28,"area":null},{"id":"2210.06475","title":"Equi-Tuning: Group Equivariant Fine-Tuning of Pretrained Models","created":"2022-10-13","cited_by_count":22,"area":null},{"id":"2109.15256","title":"Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks","created":"2021-09-30","cited_by_count":19,"area":null},{"id":"2406.08787","title":"A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practices","created":"2024-06-13","cited_by_count":15,"area":null},{"id":"2107.01366","title":"Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN","created":"2021-07-03","cited_by_count":14,"area":null},{"id":"2210.01603","title":"Neural-Symbolic Recursive Machine for Systematic Generalization","created":"2022-10-04","cited_by_count":12,"area":null},{"id":"2206.04751","title":"Defending Compositionality in Emergent Languages","created":"2022-06-09","cited_by_count":8,"area":null},{"id":"2211.15578","title":"Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality","created":"2022-11-28","cited_by_count":8,"area":null},{"id":"2405.15164","title":"From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2103.01403","title":"A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics","created":"2021-03-02","cited_by_count":6,"area":null},{"id":"2311.04420","title":"Data Factors for Better Compositional Generalization","created":"2023-11-08","cited_by_count":5,"area":null},{"id":"2203.13313","title":"Deep learning for laboratory earthquake prediction and autoregressive forecasting of fault zone stress","created":"2022-03-24","cited_by_count":4,"area":null},{"id":"2202.09717","title":"Understanding Robust Generalization in Learning Regular Languages","created":"2022-02-20","cited_by_count":3,"area":null},{"id":"2307.10799","title":"Layer-wise Representation Fusion for Compositional Generalization","created":"2023-07-20","cited_by_count":2,"area":null},{"id":"2505.13089","title":"Systematic Generalization in Language Models Scales with Information Entropy","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2402.06492","title":"Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings","created":"2024-02-09","cited_by_count":1,"area":null},{"id":"2507.21257","title":"CompoST: A Benchmark for Analyzing the Ability of LLMs To Compositionally Interpret Questions in a QALD Setting","created":"2025-07-28","cited_by_count":1,"area":null},{"id":"2502.20499","title":"Data Distributional Properties As Inductive Bias for Systematic Generalization","created":"2025-02-27","cited_by_count":0,"area":null}],"next_cursor":null}