{"list":"other","total":75,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"2112.08633","title":"Learning To Retrieve Prompts for In-Context Learning","created":"2021-12-16","cited_by_count":648},{"id":"2102.07350","title":"Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm","created":"2021-02-15","cited_by_count":606},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"2109.05093","title":"PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models","created":"2021-09-10","cited_by_count":411},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"1912.09713","title":"Measuring Compositional Generalization: A Comprehensive Method on Realistic Data","created":"2019-12-20","cited_by_count":284},{"id":"2102.01293","title":"Scaling Laws for Transfer","created":"2021-02-02","cited_by_count":272},{"id":"2010.05465","title":"COGS: A Compositional Generalization Challenge Based on Semantic Interpretation","created":"2020-10-12","cited_by_count":263},{"id":"2201.05966","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","created":"2022-01-16","cited_by_count":231},{"id":"1909.12673","title":"A Constructive Prediction of the Generalization Error Across Scales","created":"2019-09-27","cited_by_count":210},{"id":"2104.08768","title":"Constrained Language Models Yield Few-Shot Semantic Parsers","created":"2021-04-18","cited_by_count":163},{"id":"1904.09545","title":"Good-Enough Compositional Data Augmentation","created":"2019-04-21","cited_by_count":158},{"id":"2204.05832","title":"What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?","created":"2022-04-12","cited_by_count":150},{"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":"1806.09029","title":"Improving Text-to-SQL Evaluation Methodology","created":"2018-06-23","cited_by_count":135},{"id":"2009.11423","title":"Task-Oriented Dialogue as Dataflow Synthesis","created":"2020-09-24","cited_by_count":122},{"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},{"id":"1606.03622","title":"Data Recombination for Neural Semantic Parsing","created":"2016-06-11","cited_by_count":111},{"id":"2109.07740","title":"Scaling Laws for Neural Machine Translation","created":"2021-09-16","cited_by_count":111},{"id":"2109.10686","title":"Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers","created":"2021-09-22","cited_by_count":106},{"id":"2110.02095","title":"Exploring the Limits of Large Scale Pre-training","created":"2021-10-05","cited_by_count":104},{"id":"2204.00498","title":"Evaluating the Text-to-SQL Capabilities of Large Language Models","created":"2022-03-15","cited_by_count":101},{"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":"1901.01608","title":"Scaling description of generalization with number of parameters in deep learning","created":"2019-01-06","cited_by_count":83},{"id":"2008.06662","title":"Compositional Generalization via Neural-Symbolic Stack Machines","created":"2020-08-15","cited_by_count":80},{"id":"2009.06040","title":"Span-based Semantic Parsing for Compositional Generalization","created":"2020-09-13","cited_by_count":77},{"id":"2003.05562","title":"Learning Compositional Rules via Neural Program Synthesis","created":"2020-03-12","cited_by_count":74},{"id":"2108.04378","title":"Making Transformers Solve Compositional Tasks","created":"2021-08-09","cited_by_count":72},{"id":"2010.03706","title":"Learning to Recombine and Resample Data for Compositional Generalization","created":"2020-10-08","cited_by_count":65},{"id":"2106.04252","title":"Meta-Learning to Compositionally Generalize","created":"2021-06-08","cited_by_count":62},{"id":"1904.09708","title":"Compositional generalization in a deep seq2seq model by separating syntax and semantics","created":"2019-04-22","cited_by_count":56},{"id":"2104.07478","title":"Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations","created":"2021-04-15","cited_by_count":55},{"id":"2006.10627","title":"Compositional Generalization by Learning Analytical Expressions","created":"2020-06-18","cited_by_count":53},{"id":"2112.08696","title":"Few-Shot Semantic Parsing with Language Models Trained On Code","created":"2021-12-16","cited_by_count":50},{"id":"1910.02612","title":"Compositional Generalization for Primitive Substitutions","created":"2019-10-07","cited_by_count":48},{"id":"2010.07174","title":"The EOS Decision and Length Extrapolation","created":"2020-10-14","cited_by_count":46},{"id":"2112.07610","title":"Improving Compositional Generalization with Latent Structure and Data Augmentation","created":"2021-12-14","cited_by_count":46},{"id":"2010.05647","title":"Improving Compositional Generalization in Semantic Parsing","created":"2020-10-12","cited_by_count":42},{"id":"2010.11818","title":"Compositional Generalization via Semantic Tagging","created":"2020-10-22","cited_by_count":32},{"id":"2201.05899","title":"Unobserved Local Structures Make Compositional Generalization Hard","created":"2022-01-15","cited_by_count":29},{"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":"1908.09940","title":"Don't paraphrase, detect! Rapid and Effective Data Collection for Semantic Parsing","created":"2019-08-26","cited_by_count":24},{"id":"2009.12583","title":"Small Data, Big Decisions: Model Selection in the Small-Data Regime","created":"2020-09-26","cited_by_count":23},{"id":"2202.06387","title":"Scaling Laws Under the Microscope: Predicting Transformer Performance from Small Scale Experiments","created":"2022-02-13","cited_by_count":23},{"id":"2110.08525","title":"The Power of Prompt Tuning for Low-Resource Semantic Parsing","created":"2021-10-16","cited_by_count":21},{"id":"2109.15256","title":"Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks","created":"2021-09-30","cited_by_count":19},{"id":"2106.03257","title":"Structured Reordering for Modeling Latent Alignments in Sequence Transduction","created":"2021-06-06","cited_by_count":17},{"id":"2012.08266","title":"*-CFQ: Analyzing the Scalability of Machine Learning on a Compositional Task","created":"2020-12-15","cited_by_count":16},{"id":"2205.01538","title":"SUBS: Subtree Substitution for Compositional Semantic Parsing","created":"2022-05-03","cited_by_count":16},{"id":"2110.04169","title":"Iterative Decoding for Compositional Generalization in Transformers","created":"2021-10-08","cited_by_count":6},{"id":"2111.05013","title":"Learning to Generalize Compositionally by Transferring Across Semantic Parsing Tasks","created":"2021-11-09","cited_by_count":6}],"next_cursor":null}