{"list":"other","total":88,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"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":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"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":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1911.00536","title":"DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation","created":"2019-11-01","cited_by_count":842},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"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":"1909.05858","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","created":"2019-09-11","cited_by_count":762},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"2004.13637","title":"Recipes for building an open-domain chatbot","created":"2020-04-28","cited_by_count":593},{"id":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"id":"1811.01241","title":"Wizard of Wikipedia: Knowledge-Powered Conversational agents","created":"2018-11-03","cited_by_count":530},{"id":"2102.01454","title":"MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers","created":"2021-02-02","cited_by_count":470},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460},{"id":"2007.07779","title":"AdapterHub: A Framework for Adapting Transformers","created":"2020-07-15","cited_by_count":444},{"id":"2105.03023","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","created":"2021-05-07","cited_by_count":441},{"id":"2206.05802","title":"Self-critiquing models for assisting human evaluators","created":"2022-06-12","cited_by_count":380},{"id":"2009.06367","title":"GeDi: Generative Discriminator Guided Sequence Generation","created":"2020-09-14","cited_by_count":378},{"id":"2104.05218","title":"FUDGE: Controlled Text Generation With Future Discriminators","created":"2021-04-12","cited_by_count":376},{"id":"1804.08838","title":"Measuring the Intrinsic Dimension of Objective Landscapes","created":"2018-04-24","cited_by_count":370},{"id":"1705.04304","title":"A Deep Reinforced Model for Abstractive Summarization","created":"2017-05-11","cited_by_count":365},{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344},{"id":"2109.01247","title":"Do Prompt-Based Models Really Understand the Meaning of their Prompts?","created":"2021-09-02","cited_by_count":326},{"id":"1606.01541","title":"Deep Reinforcement Learning for Dialogue Generation","created":"2016-06-05","cited_by_count":288},{"id":"2211.00053","title":"Generating Sequences by Learning to Self-Correct","created":"2022-10-31","cited_by_count":277},{"id":"2110.07178","title":"Symbolic Knowledge Distillation: from General Language Models to Commonsense Models","created":"2021-10-14","cited_by_count":270},{"id":"2210.07197","title":"Towards a Unified Multi-Dimensional Evaluator for Text Generation","created":"2022-10-13","cited_by_count":264},{"id":"2112.12870","title":"Measuring Attribution in Natural Language Generation Models","created":"2021-12-23","cited_by_count":256},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247},{"id":"2210.01241","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","created":"2022-10-03","cited_by_count":246},{"id":"1704.07138","title":"Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search","created":"2017-04-24","cited_by_count":237},{"id":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237},{"id":"2202.06417","title":"A Contrastive Framework for Neural Text Generation","created":"2022-02-13","cited_by_count":225},{"id":"2210.06774","title":"Re3: Generating Longer Stories With Recursive Reprompting and Revision","created":"2022-10-13","cited_by_count":193},{"id":"1909.05398","title":"Interactive Fiction Games: A Colossal Adventure","created":"2019-09-11","cited_by_count":168},{"id":"2202.11705","title":"COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics","created":"2022-02-23","cited_by_count":161},{"id":"2010.12884","title":"NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints","created":"2020-10-24","cited_by_count":149},{"id":"2104.08704","title":"A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation","created":"2021-04-18","cited_by_count":138},{"id":"2204.07931","title":"On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?","created":"2022-04-17","cited_by_count":138},{"id":"2206.11871","title":"Offline RL for Natural Language Generation with Implicit Language Q Learning","created":"2022-06-05","cited_by_count":138},{"id":"2205.11275","title":"RL with KL penalties is better viewed as Bayesian inference","created":"2022-05-23","cited_by_count":135},{"id":"2201.05337","title":"A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models","created":"2022-01-14","cited_by_count":129},{"id":"2202.00666","title":"Locally Typical Sampling","created":"2022-02-01","cited_by_count":111},{"id":"2204.10757","title":"FaithDial: A Faithful Benchmark for Information-Seeking Dialogue","created":"2022-04-22","cited_by_count":109},{"id":"2205.12688","title":"ProsocialDialog: A Prosocial Backbone for Conversational Agents","created":"2022-05-25","cited_by_count":109},{"id":"2005.10636","title":"Graph-based, Self-Supervised Program Repair from Diagnostic Feedback","created":"2020-05-20","cited_by_count":94},{"id":"2208.11663","title":"PEER: A Collaborative Language Model","created":"2022-08-24","cited_by_count":86},{"id":"1907.01752","title":"On the Weaknesses of Reinforcement Learning for Neural Machine Translation","created":"2019-07-03","cited_by_count":82},{"id":"2105.00071","title":"Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark","created":"2021-04-30","cited_by_count":77},{"id":"2004.14589","title":"Improved Natural Language Generation via Loss Truncation","created":"2020-04-30","cited_by_count":75},{"id":"2107.06963","title":"Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features","created":"2021-07-14","cited_by_count":74},{"id":"1906.02768","title":"Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP","created":"2019-06-06","cited_by_count":73},{"id":"2110.08466","title":"On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark","created":"2021-10-16","cited_by_count":73},{"id":"1707.07402","title":"Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback","created":"2017-07-24","cited_by_count":72},{"id":"1506.08941","title":"Language Understanding for Text-based Games Using Deep Reinforcement Learning","created":"2015-06-30","cited_by_count":71},{"id":"2108.01850","title":"Controlled Text Generation as Continuous Optimization with Multiple Constraints","created":"2021-08-04","cited_by_count":70},{"id":"2203.13299","title":"Mix and Match: Learning-free Controllable Text Generation using Energy Language Models","created":"2022-03-24","cited_by_count":66},{"id":"2010.05906","title":"Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning","created":"2020-10-12","cited_by_count":65},{"id":"1811.05249","title":"Modular Networks: Learning to Decompose Neural Computation","created":"2018-11-13","cited_by_count":62},{"id":"2206.11309","title":"GODEL: Large-Scale Pre-Training for Goal-Directed Dialog","created":"2022-06-22","cited_by_count":51},{"id":"1904.12774","title":"Routing Networks and the Challenges of Modular and Compositional Computation","created":"2019-04-29","cited_by_count":50},{"id":"2106.07704","title":"Efficient (Soft) Q-Learning for Text Generation with Limited Good Data","created":"2021-06-14","cited_by_count":37},{"id":"1807.04640","title":"Automatically Composing Representation Transformations as a Means for Generalization","created":"2018-07-12","cited_by_count":35},{"id":"2106.08942","title":"Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation","created":"2021-06-16","cited_by_count":33},{"id":"2303.10475","title":"Large Language Model Instruction Following: A Survey of Progresses and Challenges","created":"2023-03-18","cited_by_count":31},{"id":"2104.12714","title":"Focused Attention Improves Document-Grounded Generation","created":"2021-04-26","cited_by_count":24},{"id":"1712.02838","title":"End-to-End Offline Goal-Oriented Dialog Policy Learning via Policy Gradient","created":"2017-12-07","cited_by_count":23},{"id":"2212.10466","title":"Controllable Text Generation with Language Constraints","created":"2022-12-20","cited_by_count":18}],"next_cursor":null}