{"total":263,"rows":[{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459,"area":null},{"id":"2210.09150","title":"Prompting GPT-3 To Be Reliable","created":"2022-10-17","cited_by_count":260,"area":null},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161,"area":null},{"id":"2407.03978","title":"Benchmarking Complex Instruction-Following with Multiple Constraints Composition","created":"2024-07-04","cited_by_count":152,"area":null},{"id":"2111.09509","title":"How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN","created":"2021-11-18","cited_by_count":124,"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":"2208.07998","title":"What Artificial Neural Networks Can Tell Us About Human Language Acquisition","created":"2022-08-17","cited_by_count":99,"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":"2209.15003","title":"Compositional Semantic Parsing with Large Language Models","created":"2022-09-29","cited_by_count":95,"area":null},{"id":"2303.07971","title":"A Theory of Emergent In-Context Learning as Implicit Structure Induction","created":"2023-03-14","cited_by_count":86,"area":null},{"id":"2108.04378","title":"Making Transformers Solve Compositional Tasks","created":"2021-08-09","cited_by_count":72,"area":null},{"id":"2411.04986","title":"The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities","created":"2024-11-07","cited_by_count":69,"area":null},{"id":"2107.07150","title":"Tailor: Generating and Perturbing Text with Semantic Controls","created":"2021-07-15","cited_by_count":68,"area":null},{"id":"2401.14295","title":"Demystifying Chains, Trees, and Graphs of Thoughts","created":"2024-01-25","cited_by_count":63,"area":"lr"},{"id":"2106.04252","title":"Meta-Learning to Compositionally Generalize","created":"2021-06-08","cited_by_count":62,"area":null},{"id":"2108.05885","title":"The paradox of the compositionality of natural language: a neural machine translation case study","created":"2021-08-12","cited_by_count":59,"area":null},{"id":"2109.07020","title":"Frequency Effects on Syntactic Rule Learning in Transformers","created":"2021-09-14","cited_by_count":59,"area":null},{"id":"2506.17267","title":"CF-VLM:CounterFactual Vision-Language Fine-tuning","created":"2025-06-10","cited_by_count":59,"area":"lr"},{"id":"2205.12411","title":"Linear Connectivity Reveals Generalization Strategies","created":"2022-05-24","cited_by_count":56,"area":null},{"id":"2305.04835","title":"How Do In-Context Examples Affect Compositional Generalization?","created":"2023-05-08","cited_by_count":51,"area":"lr"},{"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":"2305.14210","title":"Skill-Based Few-Shot Selection for In-Context Learning","created":"2023-05-23","cited_by_count":46,"area":null},{"id":"2205.01128","title":"Neurocompositional computing: From the Central Paradox of Cognition to a new generation of AI systems","created":"2022-05-02","cited_by_count":44,"area":null},{"id":"2211.00768","title":"Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality","created":"2022-11-01","cited_by_count":44,"area":null},{"id":"2301.10884","title":"Break It Down: Evidence for Structural Compositionality in Neural Networks","created":"2023-01-26","cited_by_count":44,"area":null},{"id":"2211.01288","title":"Characterizing Intrinsic Compositionality in Transformers with Tree Projections","created":"2022-11-02","cited_by_count":41,"area":null},{"id":"2407.15720","title":"Do Large Language Models Have Compositional Ability? An Investigation into Limitations and Scalability","created":"2024-07-22","cited_by_count":40,"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":"2403.05110","title":"Efficient Data Collection for Robotic Manipulation via Compositional Generalization","created":"2024-03-08","cited_by_count":37,"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":"2405.15750","title":"Filtered Corpus Training (FiCT) Shows that Language Models can Generalize from Indirect Evidence","created":"2024-05-24","cited_by_count":35,"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":"2203.09978","title":"WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series","created":"2022-03-18","cited_by_count":30,"area":null},{"id":"2504.05081","title":"The Curse of CoT: On the Limitations of Chain-of-Thought in In-Context Learning","created":"2025-04-07","cited_by_count":30,"area":"lr"},{"id":"2110.02782","title":"How BPE Affects Memorization in Transformers","created":"2021-10-06","cited_by_count":29,"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":"2409.04556","title":"How Does Code Pretraining Affect Language Model Task Performance?","created":"2024-09-06","cited_by_count":28,"area":null},{"id":"2105.03322","title":"Are Pre-trained Convolutions Better than Pre-trained Transformers?","created":"2021-05-07","cited_by_count":27,"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":"2109.13986","title":"Symbolic Brittleness in Sequence Models: on Systematic Generalization in Symbolic Mathematics","created":"2021-09-28","cited_by_count":27,"area":null},{"id":"2206.05056","title":"On Neural Architecture Inductive Biases for Relational Tasks","created":"2022-06-09","cited_by_count":26,"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":"2109.10613","title":"COVR: A test-bed for Visually Grounded Compositional Generalization with real images","created":"2021-09-22","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":"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":"2208.10244","title":"Unit Testing for Concepts in Neural Networks","created":"2022-07-28","cited_by_count":23,"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":"2310.15040","title":"SLOG: A Structural Generalization Benchmark for Semantic Parsing","created":"2023-10-23","cited_by_count":22,"area":null},{"id":"2402.04875","title":"On Provable Length and Compositional Generalization","created":"2024-02-07","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":"2501.08537","title":"Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers","created":"2025-01-15","cited_by_count":20,"area":null},{"id":"2502.18795","title":"Anything Goes? A Crosslinguistic Study of (Im)possible Language Learning in LMs","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2109.12036","title":"Transformers Generalize Linearly","created":"2021-09-24","cited_by_count":19,"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":"2110.08467","title":"Improving Compositional Generalization with Self-Training for Data-to-Text Generation","created":"2021-10-16","cited_by_count":19,"area":null},{"id":"2410.12656","title":"Evaluating Morphological Compositional Generalization in Large Language Models","created":"2024-10-16","cited_by_count":19,"area":null},{"id":"2412.04703","title":"Transformers Struggle to Learn to Search","created":"2024-12-06","cited_by_count":19,"area":null},{"id":"2506.22598","title":"RExBench: Can coding agents autonomously implement AI research extensions?","created":"2025-06-27","cited_by_count":18,"area":"agents"},{"id":"2212.08286","title":"ALERT: Adapting Language Models to Reasoning Tasks","created":"2022-12-16","cited_by_count":17,"area":"lr"},{"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":"2405.05409","title":"Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing","created":"2024-05-08","cited_by_count":17,"area":null},{"id":"2306.00824","title":"Zero and Few-shot Semantic Parsing with Ambiguous Inputs","created":"2023-06-01","cited_by_count":16,"area":null},{"id":"2101.10713","title":"Exploring Transitivity in Neural NLI Models through Veridicality","created":"2021-01-26","cited_by_count":15,"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":"2112.03204","title":"Quantifying Adaptability in Pre-trained Language Models with 500 Tasks","created":"2021-12-06","cited_by_count":13,"area":null},{"id":"2202.10745","title":"Improving Systematic Generalization Through Modularity and Augmentation","created":"2022-02-22","cited_by_count":13,"area":null},{"id":"2302.12239","title":"What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structure","created":"2023-02-23","cited_by_count":13,"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":"2402.05785","title":"Limits of Transformer Language Models on Learning to Compose Algorithms","created":"2024-02-08","cited_by_count":13,"area":null},{"id":"2410.06303","title":"Compositional Risk Minimization","created":"2024-10-08","cited_by_count":13,"area":null},{"id":"2210.01603","title":"Neural-Symbolic Recursive Machine for Systematic Generalization","created":"2022-10-04","cited_by_count":12,"area":null},{"id":"2210.06350","title":"CTL++: Evaluating Generalization on Never-Seen Compositional Patterns of Known Functions, and Compatibility of Neural Representations","created":"2022-10-12","cited_by_count":12,"area":null},{"id":"2210.09404","title":"Measures of Information Reflect Memorization Patterns","created":"2022-10-17","cited_by_count":12,"area":null},{"id":"2302.01067","title":"A Survey on Compositional Generalization in Applications","created":"2023-02-02","cited_by_count":12,"area":null},{"id":"2310.17514","title":"The Validity of Evaluation Results: Assessing Concurrence Across Compositionality Benchmarks","created":"2023-10-26","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":"2210.12786","title":"When Can Transformers Ground and Compose: Insights from Compositional Generalization Benchmarks","created":"2022-10-23","cited_by_count":11,"area":null},{"id":"2302.07866","title":"Do Deep Neural Networks Capture Compositionality in Arithmetic Reasoning?","created":"2023-02-15","cited_by_count":11,"area":"lr"},{"id":"2311.01386","title":"Can Language Models Be Tricked by Language Illusions? Easier with Syntax, Harder with Semantics","created":"2023-11-02","cited_by_count":11,"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":"2311.09519","title":"Leveraging Code to Improve In-context Learning for Semantic Parsing","created":"2023-11-16","cited_by_count":10,"area":null},{"id":"2502.13195","title":"Linguistic Generalizations are not Rules: Impacts on Evaluation of LMs","created":"2025-02-18","cited_by_count":10,"area":null},{"id":"2504.05089","title":"Climplicit: Climatic Implicit Embeddings for Global Ecological Tasks","created":"2025-04-07","cited_by_count":10,"area":null},{"id":"2108.03509","title":"Compositional Generalization in Multilingual Semantic Parsing over Wikidata","created":"2021-08-07","cited_by_count":9,"area":null},{"id":"2210.06799","title":"Benchmarking Long-tail Generalization with Likelihood Splits","created":"2022-10-13","cited_by_count":9,"area":null},{"id":"2402.11532","title":"Chain-of-Instructions: Compositional Instruction Tuning on Large Language Models","created":"2024-02-18","cited_by_count":9,"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":"2406.16135","title":"Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models","created":"2024-06-23","cited_by_count":9,"area":null},{"id":"2408.05086","title":"A systematic framework for generating novel experimental hypotheses from language models","created":"2024-08-09","cited_by_count":9,"area":null},{"id":"2501.04249","title":"IOLBENCH: Benchmarking LLMs on Linguistic Reasoning","created":"2025-01-08","cited_by_count":9,"area":"lr"},{"id":"2201.12926","title":"Compositionality as Lexical Symmetry","created":"2022-01-30","cited_by_count":8,"area":null},{"id":"2203.08445","title":"Structurally Diverse Sampling for Sample-Efficient Training and Comprehensive Evaluation","created":"2022-03-16","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}],"next_cursor":"100"}