{"list":"other","total":51,"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":"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":"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":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"1705.08690","title":"Continual Learning with Deep Generative Replay","created":"2017-05-24","cited_by_count":1158},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"2301.10226","title":"A Watermark for Large Language Models","created":"2023-01-24","cited_by_count":725},{"id":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721},{"id":"1511.06349","title":"Generating Sentences from a Continuous Space","created":"2015-11-19","cited_by_count":612},{"id":"2201.11990","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","created":"2022-01-28","cited_by_count":559},{"id":"2206.14576","title":"Using cognitive psychology to understand GPT-3","created":"2022-06-21","cited_by_count":398},{"id":"1609.05473","title":"SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient","created":"2016-09-18","cited_by_count":376},{"id":"2201.06796","title":"CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities","created":"2022-01-18","cited_by_count":249},{"id":"2302.02083","title":"Evaluating Large Language Models in Theory of Mind Tasks","created":"2023-02-04","cited_by_count":222},{"id":"2209.14958","title":"Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionals","created":"2022-09-29","cited_by_count":191},{"id":"2212.03551","title":"Talking About Large Language Models","created":"2022-12-07","cited_by_count":175},{"id":"1909.03329","title":"LAMOL: LAnguage MOdeling for Lifelong Language Learning","created":"2019-09-07","cited_by_count":160},{"id":"2102.02503","title":"Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models","created":"2021-02-04","cited_by_count":160},{"id":"2111.09509","title":"How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN","created":"2021-11-18","cited_by_count":124},{"id":"2004.14967","title":"PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking","created":"2020-04-30","cited_by_count":105},{"id":"2110.07640","title":"Sparks: Inspiration for Science Writing using Language Models","created":"2021-10-14","cited_by_count":80},{"id":"2210.07321","title":"Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods","created":"2022-10-13","cited_by_count":79},{"id":"2210.13669","title":"Help me write a poem: Instruction Tuning as a Vehicle for Collaborative Poetry Writing","created":"2022-10-25","cited_by_count":71},{"id":"2211.05030","title":"Creative Writing with an AI-Powered Writing Assistant: Perspectives from Professional Writers","created":"2022-11-09","cited_by_count":69},{"id":"1706.01331","title":"Event Representations for Automated Story Generation with Deep Neural Nets","created":"2017-06-05","cited_by_count":63},{"id":"2206.08932","title":"Putting GPT-3's Creativity to the (Alternative Uses) Test","created":"2022-06-10","cited_by_count":62},{"id":"1401.3841","title":"Narrative Planning: Balancing Plot and Character","created":"2014-01-16","cited_by_count":61},{"id":"1706.03850","title":"Adversarial Feature Matching for Text Generation","created":"2017-06-12","cited_by_count":58},{"id":"2003.02498","title":"RecipeGPT: Generative Pre-training Based Cooking Recipe Generation and Evaluation System","created":"2020-03-05","cited_by_count":34},{"id":"1702.02390","title":"A Hybrid Convolutional Variational Autoencoder for Text Generation","created":"2017-02-08","cited_by_count":33},{"id":"2209.03118","title":"The Ethical Need for Watermarks in Machine-Generated Language","created":"2022-09-07","cited_by_count":32},{"id":"2105.09266","title":"Copyright in Generative Deep Learning","created":"2021-05-19","cited_by_count":29},{"id":"2104.02726","title":"Creativity and Machine Learning: A Survey","created":"2021-04-06","cited_by_count":21},{"id":"2102.06391","title":"Multiversal views on language models","created":"2021-02-12","cited_by_count":6},{"id":"2301.05133","title":"Is AI Art Another Industrial Revolution in the Making?","created":"2023-01-12","cited_by_count":5}],"next_cursor":null}