{"list":"other","total":51,"rows":[{"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":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1803.02999","title":"On First-Order Meta-Learning Algorithms","created":"2018-03-08","cited_by_count":1018},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621},{"id":"1802.10026","title":"Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs","created":"2018-02-27","cited_by_count":588},{"id":"1602.01585","title":"Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering","created":"2016-02-04","cited_by_count":520},{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"1808.09121","title":"WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations","created":"2018-08-28","cited_by_count":372},{"id":"1307.5336","title":"Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Texts","created":"2013-07-19","cited_by_count":310},{"id":"1904.03626","title":"On The Power of Curriculum Learning in Training Deep Networks","created":"2019-04-07","cited_by_count":286},{"id":"1902.09666","title":"Predicting the Type and Target of Offensive Posts in Social Media","created":"2019-02-25","cited_by_count":271},{"id":"1811.01088","title":"Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks","created":"2018-11-02","cited_by_count":215},{"id":"1912.00741","title":"SemEval-2017 Task 4: Sentiment Analysis in Twitter","created":"2019-12-02","cited_by_count":210},{"id":"2101.11038","title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","created":"2021-01-26","cited_by_count":192},{"id":"2208.03306","title":"Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models","created":"2022-08-05","cited_by_count":191},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161},{"id":"2010.04495","title":"Linear Mode Connectivity in Multitask and Continual Learning","created":"2020-10-09","cited_by_count":145},{"id":"1710.06451","title":"A Bayesian Perspective on Generalization and Stochastic Gradient Descent","created":"2017-10-17","cited_by_count":135},{"id":"2211.08403","title":"REPAIR: REnormalizing Permuted Activations for Interpolation Repair","created":"2022-11-15","cited_by_count":120},{"id":"2204.03044","title":"Fusing finetuned models for better pretraining","created":"2022-04-06","cited_by_count":110},{"id":"2103.02631","title":"RotoGrad: Gradient Homogenization in Multitask Learning","created":"2021-03-03","cited_by_count":83},{"id":"2202.07962","title":"Revisiting Parameter-Efficient Tuning: Are We Really There Yet?","created":"2022-02-16","cited_by_count":76},{"id":"2102.13042","title":"Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling","created":"2021-02-25","cited_by_count":75},{"id":"1911.03863","title":"Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks","created":"2019-11-10","cited_by_count":57},{"id":"2205.12411","title":"Linear Connectivity Reveals Generalization Strategies","created":"2022-05-24","cited_by_count":56},{"id":"2211.08422","title":"Mechanistic Mode Connectivity","created":"2022-11-15","cited_by_count":50},{"id":"2011.02686","title":"Investigating Societal Biases in a Poetry Composition System","created":"2020-11-05","cited_by_count":48},{"id":"2109.06096","title":"The Grammar-Learning Trajectories of Neural Language Models","created":"2021-09-13","cited_by_count":36},{"id":"1708.03696","title":"Emotion Intensities in Tweets","created":"2017-08-11","cited_by_count":32},{"id":"2210.14102","title":"Exploring Mode Connectivity for Pre-trained Language Models","created":"2022-10-25","cited_by_count":26},{"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":"2211.00107","title":"Where to start? Analyzing the potential value of intermediate models","created":"2022-10-31","cited_by_count":23},{"id":"2210.11948","title":"lo-fi: distributed fine-tuning without communication","created":"2022-10-19","cited_by_count":19}],"next_cursor":null}