{"total":62,"rows":[{"id":"2305.19466","title":"The Impact of Positional Encoding on Length Generalization in Transformers","created":"2023-05-31","cited_by_count":327,"area":null},{"id":"2307.03381","title":"Teaching Arithmetic to Small Transformers","created":"2023-07-07","cited_by_count":123,"area":null},{"id":"2108.12284","title":"The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers","created":"2021-08-26","cited_by_count":117,"area":null},{"id":"2305.16843","title":"Randomized Positional Encodings Boost Length Generalization of Transformers","created":"2023-05-26","cited_by_count":117,"area":null},{"id":"2204.03044","title":"Fusing finetuned models for better pretraining","created":"2022-04-06","cited_by_count":110,"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":"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":"2205.12253","title":"Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing","created":"2022-05-24","cited_by_count":50,"area":null},{"id":"2112.07610","title":"Improving Compositional Generalization with Latent Structure and Data Augmentation","created":"2021-12-14","cited_by_count":46,"area":null},{"id":"2112.00578","title":"Systematic Generalization with Edge Transformers","created":"2021-12-01","cited_by_count":38,"area":null},{"id":"2310.19956","title":"The Impact of Depth on Compositional Generalization in Transformer Language Models","created":"2023-10-30","cited_by_count":38,"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":"2406.06467","title":"How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad","created":"2024-06-10","cited_by_count":36,"area":null},{"id":"2212.10769","title":"Uncontrolled Lexical Exposure Leads to Overestimation of Compositional Generalization in Pretrained Models","created":"2022-12-21","cited_by_count":26,"area":null},{"id":"2311.09817","title":"Neural-Logic Human-Object Interaction Detection","created":"2023-11-16","cited_by_count":25,"area":null},{"id":"2210.13050","title":"Structural generalization is hard for sequence-to-sequence models","created":"2022-10-24","cited_by_count":24,"area":null},{"id":"2303.13716","title":"ReCOGS: How Incidental Details of a Logical Form Overshadow an Evaluation of Semantic Interpretation","created":"2023-03-24","cited_by_count":24,"area":null},{"id":"2401.03910","title":"A Philosophical Introduction to Language Models -- Part I: Continuity With Classic Debates","created":"2024-01-08","cited_by_count":23,"area":null},{"id":"2311.12997","title":"Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks","created":"2023-11-21","cited_by_count":22,"area":null},{"id":"2203.07402","title":"Revisiting the Compositional Generalization Abilities of Neural Sequence Models","created":"2022-03-14","cited_by_count":20,"area":null},{"id":"2210.00400","title":"Systematic Generalization and Emergent Structures in Transformers Trained on Structured Tasks","created":"2022-10-02","cited_by_count":19,"area":null},{"id":"2210.12574","title":"The Curious Case of Absolute Position Embeddings","created":"2022-10-23","cited_by_count":17,"area":null},{"id":"2307.13883","title":"ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis","created":"2023-07-26","cited_by_count":17,"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":"2302.13114","title":"Sequential Query Encoding For Complex Query Answering on Knowledge Graphs","created":"2023-02-25","cited_by_count":13,"area":null},{"id":"2203.15099","title":"LogicInference: A New Dataset for Teaching Logical Inference to seq2seq Models","created":"2022-03-28","cited_by_count":12,"area":null},{"id":"2210.01603","title":"Neural-Symbolic Recursive Machine for Systematic Generalization","created":"2022-10-04","cited_by_count":12,"area":null},{"id":"2501.19215","title":"Strassen Attention, Split VC Dimension and Compositionality in Transformers","created":"2025-01-31","cited_by_count":12,"area":null},{"id":"2402.13572","title":"AlgoFormer: An Efficient Transformer Framework with Algorithmic Structures","created":"2024-02-21","cited_by_count":11,"area":null},{"id":"2402.17396","title":"Benchmarking GPT-4 on Algorithmic Problems: A Systematic Evaluation of Prompting Strategies","created":"2024-02-27","cited_by_count":9,"area":null},{"id":"2306.02840","title":"Learning to Substitute Spans towards Improving Compositional Generalization","created":"2023-06-05","cited_by_count":8,"area":null},{"id":"2502.16792","title":"The Role of Sparsity for Length Generalization in Transformers","created":"2025-02-24","cited_by_count":8,"area":null},{"id":"2110.07572","title":"LAGr: Labeling Aligned Graphs for Improving Systematic Generalization in Semantic Parsing","created":"2021-10-14","cited_by_count":7,"area":null},{"id":"2410.18077","title":"ALTA: Compiler-Based Analysis of Transformers","created":"2024-10-23","cited_by_count":7,"area":null},{"id":"2110.04169","title":"Iterative Decoding for Compositional Generalization in Transformers","created":"2021-10-08","cited_by_count":6,"area":null},{"id":"2210.03183","title":"Compositional Generalisation with Structured Reordering and Fertility Layers","created":"2022-10-06","cited_by_count":6,"area":null},{"id":"2403.11834","title":"Towards Understanding the Relationship between In-context Learning and Compositional Generalization","created":"2024-03-18","cited_by_count":5,"area":null},{"id":"2405.02350","title":"What makes Models Compositional? A Theoretical View: With Supplement","created":"2024-05-02","cited_by_count":5,"area":null},{"id":"2405.04048","title":"Philosophy of Cognitive Science in the Age of Deep Learning","created":"2024-05-07","cited_by_count":5,"area":null},{"id":"2411.05943","title":"Quantifying artificial intelligence through algorithmic generalization","created":"2024-11-08","cited_by_count":5,"area":null},{"id":"2301.03238","title":"MAQA: A Multimodal QA Benchmark for Negation","created":"2023-01-09","cited_by_count":4,"area":null},{"id":"2311.15211","title":"Probabilistic Transformer: A Probabilistic Dependency Model for Contextual Word Representation","created":"2023-11-26","cited_by_count":4,"area":null},{"id":"2506.11769","title":"Long-Short Alignment for Effective Long-Context Modeling in LLMs","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2510.14826","title":"To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models","created":"2025-10-16","cited_by_count":4,"area":null},{"id":"2405.10650","title":"SPOR: A Comprehensive and Practical Evaluation Method for Compositional Generalization in Data-to-Text Generation","created":"2024-05-17","cited_by_count":3,"area":null},{"id":"2210.06709","title":"Categorizing Semantic Representations for Neural Machine Translation","created":"2022-10-13","cited_by_count":2,"area":null},{"id":"2311.01580","title":"MetaReVision: Meta-Learning with Retrieval for Visually Grounded Compositional Concept Acquisition","created":"2023-11-02","cited_by_count":2,"area":null},{"id":"2402.17407","title":"A Neural Rewriting System to Solve Algorithmic Problems","created":"2024-02-27","cited_by_count":2,"area":null},{"id":"2509.10414","title":"Is In-Context Learning Learning?","created":"2025-09-12","cited_by_count":2,"area":null},{"id":"2201.09377","title":"An Application of Pseudo-Log-Likelihoods to Natural Language Scoring","created":"2022-01-23","cited_by_count":1,"area":null},{"id":"2312.15815","title":"Compositional Generalization in Spoken Language Understanding","created":"2023-12-25","cited_by_count":1,"area":null},{"id":"2406.08272","title":"Learning interpretable positional encodings in transformers depends on initialization","created":"2024-06-12","cited_by_count":1,"area":null},{"id":"2502.20834","title":"Learning to Substitute Components for Compositional Generalization","created":"2025-02-28","cited_by_count":1,"area":null},{"id":"2511.19328","title":"Understanding the Staged Dynamics of Transformers in Learning Latent Structure","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2205.09607","title":"LAGr: Label Aligned Graphs for Better Systematic Generalization in Semantic Parsing","created":"2022-05-19","cited_by_count":0,"area":null},{"id":"2211.11956","title":"A Short Survey of Systematic Generalization","created":"2022-11-22","cited_by_count":0,"area":null},{"id":"2406.17615","title":"Aligning Programming Language and Natural Language: Exploring Design Choices in Multi-Modal Transformer-Based Embedding for Bug Localization","created":"2024-06-25","cited_by_count":0,"area":null},{"id":"2408.00508","title":"Block-Operations: Using Modular Routing to Improve Compositional Generalization","created":"2024-08-01","cited_by_count":0,"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},{"id":"2504.15349","title":"Exploring Compositional Generalization (in COGS/ReCOGS_pos) by Transformers using Restricted Access Sequence Processing (RASP)","created":"2025-04-21","cited_by_count":0,"area":null},{"id":"2601.06914","title":"Towards Compositional Generalization in LLMs for Smart Contract Security: A Case Study on Reentrancy Vulnerabilities","created":"2026-01-11","cited_by_count":0,"area":null},{"id":"2604.15306","title":"Generalization in LLM Problem Solving: The Case of the Shortest Path","created":"2026-04-16","cited_by_count":0,"area":null}],"next_cursor":null}