{"total":86,"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":"2310.16028","title":"What Algorithms can Transformers Learn? A Study in Length Generalization","created":"2023-10-24","cited_by_count":199,"area":null},{"id":"2212.06800","title":"Diverse Demonstrations Improve In-context Compositional Generalization","created":"2022-12-13","cited_by_count":139,"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":"2104.08762","title":"Case-based Reasoning for Natural Language Queries over Knowledge Bases","created":"2021-04-18","cited_by_count":107,"area":null},{"id":"2106.07499","title":"An Empirical Survey of Data Augmentation for Limited Data Learning in NLP","created":"2021-06-14","cited_by_count":101,"area":null},{"id":"2209.15003","title":"Compositional Semantic Parsing with Large Language Models","created":"2022-09-29","cited_by_count":95,"area":null},{"id":"2108.04378","title":"Making Transformers Solve Compositional Tasks","created":"2021-08-09","cited_by_count":72,"area":null},{"id":"2106.04252","title":"Meta-Learning to Compositionally Generalize","created":"2021-06-08","cited_by_count":62,"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":"2104.07478","title":"Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations","created":"2021-04-15","cited_by_count":55,"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":"2205.07381","title":"SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models","created":"2022-05-15","cited_by_count":38,"area":null},{"id":"2204.12793","title":"Modern Baselines for SPARQL Semantic Parsing","created":"2022-04-27","cited_by_count":34,"area":null},{"id":"2107.06516","title":"Learning Algebraic Recombination for Compositional Generalization","created":"2021-07-14","cited_by_count":31,"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":"2110.04655","title":"Disentangled Sequence to Sequence Learning for Compositional Generalization","created":"2021-10-09","cited_by_count":30,"area":null},{"id":"2201.05899","title":"Unobserved Local Structures Make Compositional Generalization Hard","created":"2022-01-15","cited_by_count":29,"area":null},{"id":"2106.03993","title":"Lexicon Learning for Few-Shot Neural Sequence Modeling","created":"2021-06-07","cited_by_count":28,"area":null},{"id":"2109.02575","title":"Finding needles in a haystack: Sampling Structurally-diverse Training Sets from Synthetic Data for Compositional Generalization","created":"2021-09-06","cited_by_count":27,"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":"2102.03406","title":"Symbolic Behaviour in Artificial Intelligence","created":"2021-02-05","cited_by_count":25,"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":"2211.08473","title":"On the Compositional Generalization Gap of In-Context Learning","created":"2022-11-15","cited_by_count":24,"area":null},{"id":"2303.01580","title":"Mixture of Soft Prompts for Controllable Data Generation","created":"2023-03-02","cited_by_count":23,"area":null},{"id":"2205.14288","title":"Few-shot Subgoal Planning with Language Models","created":"2022-05-28","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":"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":"2307.13883","title":"ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis","created":"2023-07-26","cited_by_count":17,"area":null},{"id":"2205.02054","title":"Measuring and Improving Compositional Generalization in Text-to-SQL via Component Alignment","created":"2022-05-04","cited_by_count":16,"area":null},{"id":"2412.18702","title":"CypherBench: Towards Precise Retrieval over Full-scale Modern Knowledge Graphs in the LLM Era","created":"2024-12-24","cited_by_count":16,"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":"2202.10745","title":"Improving Systematic Generalization Through Modularity and Augmentation","created":"2022-02-22","cited_by_count":13,"area":null},{"id":"2205.12078","title":"GraphQ IR: Unifying the Semantic Parsing of Graph Query Languages with One Intermediate Representation","created":"2022-05-24","cited_by_count":13,"area":null},{"id":"2406.05816","title":"Attention as a Hypernetwork","created":"2024-06-09","cited_by_count":13,"area":null},{"id":"2106.10434","title":"Improving Compositional Generalization in Classification Tasks via Structure Annotations","created":"2021-06-19","cited_by_count":12,"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":"2305.05050","title":"ANALOGICAL -- A Novel Benchmark for Long Text Analogy Evaluation in Large Language Models","created":"2023-05-08","cited_by_count":12,"area":null},{"id":"2110.14266","title":"SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoning","created":"2021-10-27","cited_by_count":10,"area":null},{"id":"2208.11445","title":"Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Models","created":"2022-08-24","cited_by_count":10,"area":null},{"id":"2301.12217","title":"Semantic Parsing for Conversational Question Answering over Knowledge Graphs","created":"2023-01-28","cited_by_count":10,"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":"2306.02840","title":"Learning to Substitute Spans towards Improving Compositional Generalization","created":"2023-06-05","cited_by_count":8,"area":null},{"id":"2510.01685","title":"How Do Language Models Compose Functions?","created":"2025-10-02","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":"2112.05209","title":"Compositional Generalization for Natural Language Interfaces to Web APIs","created":"2021-12-09","cited_by_count":7,"area":null},{"id":"2210.12674","title":"Towards Generalizable and Robust Text-to-SQL Parsing","created":"2022-10-23","cited_by_count":7,"area":null},{"id":"2310.00796","title":"SIP: Injecting a Structural Inductive Bias into a Seq2Seq Model by Simulation","created":"2023-10-01","cited_by_count":7,"area":null},{"id":"2312.11276","title":"Compositional Generalization for Multi-label Text Classification: A Data-Augmentation Approach","created":"2023-12-18","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":"2507.07207","title":"Scaling can lead to compositional generalization","created":"2025-07-09","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":"2110.04169","title":"Iterative Decoding for Compositional Generalization in Transformers","created":"2021-10-08","cited_by_count":6,"area":null},{"id":"2111.03642","title":"Grounded Graph Decoding Improves Compositional Generalization in Question Answering","created":"2021-11-05","cited_by_count":6,"area":null},{"id":"2111.05013","title":"Learning to Generalize Compositionally by Transferring Across Semantic Parsing Tasks","created":"2021-11-09","cited_by_count":6,"area":null},{"id":"2204.03758","title":"Compositional Generalization and Decomposition in Neural Program Synthesis","created":"2022-04-07","cited_by_count":6,"area":null},{"id":"2109.15101","title":"Compositional generalization in semantic parsing with pretrained transformers","created":"2021-09-30","cited_by_count":5,"area":null},{"id":"2311.04420","title":"Data Factors for Better Compositional Generalization","created":"2023-11-08","cited_by_count":5,"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":"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":"2412.14076","title":"Compositional Generalization Across Distributional Shifts with Sparse Tree Operations","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2110.06843","title":"Compositional Generalization in Dependency Parsing","created":"2021-10-13","cited_by_count":4,"area":null},{"id":"2301.03238","title":"MAQA: A Multimodal QA Benchmark for Negation","created":"2023-01-09","cited_by_count":4,"area":null},{"id":"2310.15541","title":"Improving Language Models Meaning Understanding and Consistency by Learning Conceptual Roles from Dictionary","created":"2023-10-24","cited_by_count":4,"area":null},{"id":"2407.04543","title":"Strengthening Structural Inductive Biases by Pre-training to Perform Syntactic Transformations","created":"2024-07-05","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":"2305.12169","title":"Learning to Compose Representations of Different Encoder Layers towards Improving Compositional Generalization","created":"2023-05-20","cited_by_count":3,"area":null},{"id":"2305.19734","title":"Knowledge Base Question Answering for Space Debris Queries","created":"2023-05-31","cited_by_count":3,"area":null},{"id":"2305.04346","title":"Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic Parsing","created":"2023-05-07","cited_by_count":2,"area":null},{"id":"2307.01446","title":"On Conditional and Compositional Language Model Differentiable Prompting","created":"2023-07-04","cited_by_count":2,"area":null},{"id":"2307.10799","title":"Layer-wise Representation Fusion for Compositional Generalization","created":"2023-07-20","cited_by_count":2,"area":null},{"id":"2310.12118","title":"Harnessing Dataset Cartography for Improved Compositional Generalization in Transformers","created":"2023-10-18","cited_by_count":2,"area":null},{"id":"2208.09180","title":"Effective Transfer Learning for Low-Resource Natural Language Understanding","created":"2022-08-19","cited_by_count":1,"area":null},{"id":"2305.14104","title":"Out-of-Distribution Generalization in Text Classification: Past, Present, and Future","created":"2023-05-23","cited_by_count":1,"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":"2502.20834","title":"Learning to Substitute Components for Compositional Generalization","created":"2025-02-28","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":"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":"2302.11054","title":"Conversational Text-to-SQL: An Odyssey into State-of-the-Art and Challenges Ahead","created":"2023-02-21","cited_by_count":0,"area":null},{"id":"2306.09005","title":"Modularity Trumps Invariance for Compositional Robustness","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2511.20194","title":"In-Context Compositional Learning via Sparse Coding Transformer","created":"2025-11-25","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}