{"list":"other","total":51,"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"2002.08910","title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","created":"2020-02-10","cited_by_count":719},{"id":"2009.02252","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","created":"2020-09-04","cited_by_count":573},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"1905.08094","title":"Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation","created":"2019-05-17","cited_by_count":497},{"id":"2212.08410","title":"Teaching Small Language Models to Reason","created":"2022-12-16","cited_by_count":284},{"id":"2102.01293","title":"Scaling Laws for Transfer","created":"2021-02-02","cited_by_count":272},{"id":"2103.06268","title":"CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review","created":"2021-03-10","cited_by_count":236},{"id":"2103.08541","title":"Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence","created":"2021-03-15","cited_by_count":225},{"id":"2108.13487","title":"Want To Reduce Labeling Cost? GPT-3 Can Help","created":"2021-08-30","cited_by_count":196},{"id":"2106.05945","title":"Does Knowledge Distillation Really Work?","created":"2021-06-10","cited_by_count":190},{"id":"2204.00408","title":"Structured Pruning Learns Compact and Accurate Models","created":"2022-04-01","cited_by_count":170},{"id":"2010.03058","title":"Characterising Bias in Compressed Models","created":"2020-10-06","cited_by_count":167},{"id":"2108.04106","title":"Noisy Channel Language Model Prompting for Few-Shot Text Classification","created":"2021-08-09","cited_by_count":165},{"id":"2112.06598","title":"WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models","created":"2021-12-13","cited_by_count":89},{"id":"2104.07705","title":"How to Train BERT with an Academic Budget","created":"2021-04-15","cited_by_count":80},{"id":"2011.14826","title":"Revisiting Rainbow: Promoting more Insightful and Inclusive Deep Reinforcement Learning Research","created":"2020-11-20","cited_by_count":78},{"id":"2205.00049","title":"Prompt Consistency for Zero-Shot Task Generalization","created":"2022-04-29","cited_by_count":67},{"id":"2106.04570","title":"BERT Learns to Teach: Knowledge Distillation with Meta Learning","created":"2021-06-08","cited_by_count":61},{"id":"2006.04102","title":"Language Models as Fact Checkers?","created":"2020-06-07","cited_by_count":51},{"id":"2202.07105","title":"A Survey on Model Compression and Acceleration for Pretrained Language Models","created":"2022-02-15","cited_by_count":45},{"id":"2109.04408","title":"Learning with Different Amounts of Annotation: From Zero to Many Labels","created":"2021-09-09","cited_by_count":28},{"id":"2109.04711","title":"Pre-train or Annotate? Domain Adaptation with a Constrained Budget","created":"2021-09-10","cited_by_count":27},{"id":"2105.03536","title":"Pareto-Optimal Quantized ResNet Is Mostly 4-bit","created":"2021-05-07","cited_by_count":26},{"id":"2110.04374","title":"A Few More Examples May Be Worth Billions of Parameters","created":"2021-10-08","cited_by_count":19},{"id":"2010.12885","title":"Unsupervised Paraphrasing with Pretrained Language Models","created":"2020-10-24","cited_by_count":15},{"id":"2109.12188","title":"Predicting Attention Sparsity in Transformers","created":"2021-09-24","cited_by_count":13},{"id":"2110.08355","title":"Clean or Annotate: How to Spend a Limited Data Collection Budget","created":"2021-10-15","cited_by_count":10},{"id":"2210.03690","title":"Few-Shot Anaphora Resolution in Scientific Protocols via Mixtures of In-Context Experts","created":"2022-10-07","cited_by_count":10},{"id":"2210.03235","title":"Improving Large-scale Paraphrase Acquisition and Generation","created":"2022-10-06","cited_by_count":8},{"id":"2010.14576","title":"WNUT-2020 Task 1 Overview: Extracting Entities and Relations from Wet Lab Protocols","created":"2020-10-27","cited_by_count":5},{"id":"1906.04937","title":"Partial Or Complete, That's The Question","created":"2019-06-12","cited_by_count":4},{"id":"2110.08536","title":"Sparse Distillation: Speeding Up Text Classification by Using Bigger Student Models","created":"2021-10-16","cited_by_count":1}],"next_cursor":null}