{"list":"other","total":66,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"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":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"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":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"1506.03340","title":"Teaching Machines to Read and Comprehend","created":"2015-06-10","cited_by_count":1049},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"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":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"2009.07118","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","created":"2020-09-15","cited_by_count":669},{"id":"2104.04473","title":"Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM","created":"2021-04-09","cited_by_count":632},{"id":"1910.11856","title":"On the Cross-lingual Transferability of Monolingual Representations","created":"2019-10-25","cited_by_count":578},{"id":"1907.07374","title":"A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI","created":"2019-07-17","cited_by_count":404},{"id":"1910.07475","title":"MLQA: Evaluating Cross-lingual Extractive Question Answering","created":"2019-10-16","cited_by_count":340},{"id":"2202.06539","title":"Deduplicating Training Data Mitigates Privacy Risks in Language Models","created":"2022-02-14","cited_by_count":314},{"id":"1904.09223","title":"ERNIE: Enhanced Representation through Knowledge Integration","created":"2019-04-19","cited_by_count":302},{"id":"2004.05986","title":"CLUE: A Chinese Language Understanding Evaluation Benchmark","created":"2020-04-13","cited_by_count":278},{"id":"2004.13922","title":"Revisiting Pre-Trained Models for Chinese Natural Language Processing","created":"2020-04-29","cited_by_count":266},{"id":"2107.02137","title":"ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","created":"2021-07-05","cited_by_count":260},{"id":"2204.02329","title":"Can language models learn from explanations in context?","created":"2022-04-05","cited_by_count":249},{"id":"2011.07876","title":"A Survey on the Explainability of Supervised Machine Learning","created":"2020-11-16","cited_by_count":227},{"id":"2203.17189","title":"Scaling Up Models and Data with $\\texttt{t5x}$ and $\\texttt{seqio}$","created":"2022-03-31","cited_by_count":187},{"id":"1711.01731","title":"A Survey on Dialogue Systems: Recent Advances and New Frontiers","created":"2017-11-06","cited_by_count":162},{"id":"2011.00416","title":"Deep Learning for Text Style Transfer: A Survey","created":"2020-11-01","cited_by_count":162},{"id":"2004.14546","title":"WT5?! Training Text-to-Text Models to Explain their Predictions","created":"2020-04-30","cited_by_count":148},{"id":"2104.12369","title":"PanGu-$\\alpha$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation","created":"2021-04-26","cited_by_count":134},{"id":"2112.08674","title":"Reframing Human-AI Collaboration for Generating Free-Text Explanations","created":"2021-12-16","cited_by_count":125},{"id":"2010.11856","title":"XOR QA: Cross-lingual Open-Retrieval Question Answering","created":"2020-10-22","cited_by_count":121},{"id":"2110.14378","title":"Towards artificial general intelligence via a multimodal foundation model","created":"2021-10-27","cited_by_count":112},{"id":"1711.05073","title":"DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications","created":"2017-11-14","cited_by_count":110},{"id":"2109.03910","title":"A Recipe For Arbitrary Text Style Transfer with Large Language Models","created":"2021-09-08","cited_by_count":107},{"id":"1810.07366","title":"A Span-Extraction Dataset for Chinese Machine Reading Comprehension","created":"2018-10-17","cited_by_count":84},{"id":"1506.05865","title":"LCSTS: A Large Scale Chinese Short Text Summarization Dataset","created":"2015-06-19","cited_by_count":65},{"id":"1906.01265","title":"ChID: A Large-scale Chinese IDiom Dataset for Cloze Test","created":"2019-06-04","cited_by_count":65},{"id":"2106.16038","title":"ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information","created":"2021-06-30","cited_by_count":65},{"id":"1909.00156","title":"NCLS: Neural Cross-Lingual Summarization","created":"2019-08-31","cited_by_count":64},{"id":"2012.00413","title":"CPM: A Large-scale Generative Chinese Pre-trained Language Model","created":"2020-12-01","cited_by_count":60},{"id":"1806.00920","title":"DRCD: a Chinese Machine Reading Comprehension Dataset","created":"2018-06-04","cited_by_count":57},{"id":"2002.07526","title":"A Survey of Deep Learning Techniques for Neural Machine Translation","created":"2020-02-18","cited_by_count":50},{"id":"2112.12731","title":"ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","created":"2021-12-23","cited_by_count":46},{"id":"2006.11880","title":"A Survey on Machine Reading Comprehension: Tasks, Evaluation Metrics and Benchmark Datasets","created":"2020-06-21","cited_by_count":40},{"id":"1607.06275","title":"Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering","created":"2016-07-21","cited_by_count":35},{"id":"2110.04725","title":"Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot Learning","created":"2021-10-10","cited_by_count":35},{"id":"2205.11758","title":"Analyzing the Mono- and Cross-Lingual Pretraining Dynamics of Multilingual Language Models","created":"2022-05-24","cited_by_count":32},{"id":"2110.07385","title":"Few-shot Controllable Style Transfer for Low-Resource Multilingual Settings","created":"2021-10-14","cited_by_count":21},{"id":"1607.02250","title":"Consensus Attention-based Neural Networks for Chinese Reading Comprehension","created":"2016-07-08","cited_by_count":12},{"id":"1909.04453","title":"Select and Attend: Towards Controllable Content Selection in Text Generation","created":"2019-09-10","cited_by_count":10},{"id":"1709.08299","title":"Dataset for the First Evaluation on Chinese Machine Reading Comprehension","created":"2017-09-25","cited_by_count":9}],"next_cursor":null}