{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"1704.04368","title":"Get To The Point: Summarization with Pointer-Generator Networks","created":"2017-04-14","cited_by_count":1292},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"2211.15661","title":"What learning algorithm is in-context learning? Investigations with linear models","created":"2022-11-28","cited_by_count":684},{"id":"2304.08467","title":"Learning to Compress Prompts with Gist Tokens","created":"2023-04-17","cited_by_count":390},{"id":"2404.02060","title":"Long-context LLMs Struggle with Long In-context Learning","created":"2024-04-02","cited_by_count":286},{"id":"1912.09713","title":"Measuring Compositional Generalization: A Comprehensive Method on Realistic Data","created":"2019-12-20","cited_by_count":284},{"id":"2010.05465","title":"COGS: A Compositional Generalization Challenge Based on Semantic Interpretation","created":"2020-10-12","cited_by_count":263},{"id":"1709.03815","title":"OpenNMT: Open-source Toolkit for Neural Machine Translation","created":"2017-09-12","cited_by_count":251},{"id":"1904.09545","title":"Good-Enough Compositional Data Augmentation","created":"2019-04-21","cited_by_count":158},{"id":"2010.12725","title":"Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?","created":"2020-10-24","cited_by_count":147},{"id":"2212.06800","title":"Diverse Demonstrations Improve In-context Compositional Generalization","created":"2022-12-13","cited_by_count":139},{"id":"1806.09029","title":"Improving Text-to-SQL Evaluation Methodology","created":"2018-06-23","cited_by_count":135},{"id":"1606.03622","title":"Data Recombination for Neural Semantic Parsing","created":"2016-06-11","cited_by_count":111},{"id":"1906.05381","title":"Compositional generalization through meta sequence-to-sequence learning","created":"2019-06-12","cited_by_count":99},{"id":"2007.08970","title":"Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures","created":"2020-07-17","cited_by_count":95},{"id":"2209.15003","title":"Compositional Semantic Parsing with Large Language Models","created":"2022-09-29","cited_by_count":95},{"id":"2102.10333","title":"Provably Strict Generalisation Benefit for Equivariant Models","created":"2021-02-20","cited_by_count":91},{"id":"2005.00178","title":"On the Benefits of Invariance in Neural Networks","created":"2020-05-01","cited_by_count":79},{"id":"2009.06040","title":"Span-based Semantic Parsing for Compositional Generalization","created":"2020-09-13","cited_by_count":77},{"id":"2108.04378","title":"Making Transformers Solve Compositional Tasks","created":"2021-08-09","cited_by_count":72},{"id":"2011.09039","title":"Sequence-Level Mixed Sample Data Augmentation","created":"2020-11-18","cited_by_count":71},{"id":"2106.04252","title":"Meta-Learning to Compositionally Generalize","created":"2021-06-08","cited_by_count":62},{"id":"2305.14907","title":"Coverage-based Example Selection for In-Context Learning","created":"2023-05-24","cited_by_count":59},{"id":"2104.07478","title":"Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations","created":"2021-04-15","cited_by_count":55},{"id":"2305.04835","title":"How Do In-Context Examples Affect Compositional Generalization?","created":"2023-05-08","cited_by_count":51},{"id":"2205.12253","title":"Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing","created":"2022-05-24","cited_by_count":50},{"id":"1910.02612","title":"Compositional Generalization for Primitive Substitutions","created":"2019-10-07","cited_by_count":48},{"id":"2101.09315","title":"Tighter expected generalization error bounds via Wasserstein distance","created":"2021-01-22","cited_by_count":43},{"id":"2402.12715","title":"The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning","created":"2024-02-20","cited_by_count":41},{"id":"2110.04655","title":"Disentangled Sequence to Sequence Learning for Compositional Generalization","created":"2021-10-09","cited_by_count":30},{"id":"2201.05899","title":"Unobserved Local Structures Make Compositional Generalization Hard","created":"2022-01-15","cited_by_count":29},{"id":"2106.03993","title":"Lexicon Learning for Few-Shot Neural Sequence Modeling","created":"2021-06-07","cited_by_count":28},{"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},{"id":"2210.05021","title":"The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective","created":"2022-10-10","cited_by_count":24},{"id":"2211.08473","title":"On the Compositional Generalization Gap of In-Context Learning","created":"2022-11-15","cited_by_count":24},{"id":"2111.05529","title":"Understanding the Generalization Benefit of Model Invariance from a Data Perspective","created":"2021-11-10","cited_by_count":22},{"id":"2210.06475","title":"Equi-Tuning: Group Equivariant Fine-Tuning of Pretrained Models","created":"2022-10-13","cited_by_count":22},{"id":"2012.04276","title":"Revisiting Iterative Back-Translation from the Perspective of Compositional Generalization","created":"2020-12-08","cited_by_count":19},{"id":"2205.01538","title":"SUBS: Subtree Substitution for Compositional Semantic Parsing","created":"2022-05-03","cited_by_count":16},{"id":"2201.12926","title":"Compositionality as Lexical Symmetry","created":"2022-01-30","cited_by_count":8},{"id":"2211.15578","title":"Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality","created":"2022-11-28","cited_by_count":8},{"id":"2306.02840","title":"Learning to Substitute Spans towards Improving Compositional Generalization","created":"2023-06-05","cited_by_count":8},{"id":"2302.11978","title":"Does Deep Learning Learn to Abstract? A Systematic Probing Framework","created":"2023-02-23","cited_by_count":6},{"id":"2311.09606","title":"GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks","created":"2023-11-16","cited_by_count":6},{"id":"2401.05752","title":"Learning Generalizable Models via Disentangling Spurious and Enhancing Potential Correlations","created":"2024-01-11","cited_by_count":5},{"id":"2405.11743","title":"A General Theory for Compositional Generalization","created":"2024-05-20","cited_by_count":4},{"id":"2305.12169","title":"Learning to Compose Representations of Different Encoder Layers towards Improving Compositional Generalization","created":"2023-05-20","cited_by_count":3},{"id":"2305.13658","title":"Understanding Compositional Data Augmentation in Typologically Diverse Morphological Inflection","created":"2023-05-23","cited_by_count":3},{"id":"2307.10799","title":"Layer-wise Representation Fusion for Compositional Generalization","created":"2023-07-20","cited_by_count":2},{"id":"2310.09675","title":"Efficient Model-Agnostic Multi-Group Equivariant Networks","created":"2023-10-14","cited_by_count":1},{"id":"2312.06226","title":"Invariant Representation via Decoupling Style and Spurious Features from Images","created":"2023-12-11","cited_by_count":1},{"id":"2404.12013","title":"Sequential Compositional Generalization in Multimodal Models","created":"2024-04-18","cited_by_count":1}],"next_cursor":null}