{"list":"other","total":63,"rows":[{"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":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"1506.03099","title":"Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks","created":"2015-06-09","cited_by_count":803},{"id":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"1902.03393","title":"Improved Knowledge Distillation via Teacher Assistant","created":"2019-02-09","cited_by_count":573},{"id":"1805.04770","title":"Born Again Neural Networks","created":"2018-05-12","cited_by_count":546},{"id":"1908.09355","title":"Patient Knowledge Distillation for BERT Model Compression","created":"2019-08-25","cited_by_count":508},{"id":"1606.00709","title":"f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization","created":"2016-06-02","cited_by_count":506},{"id":"1805.01954","title":"Behavioral Cloning from Observation","created":"2018-05-04","cited_by_count":492},{"id":"1904.01685","title":"Measuring Calibration in Deep Learning","created":"2019-04-02","cited_by_count":446},{"id":"1511.06295","title":"Policy Distillation","created":"2015-11-19","cited_by_count":440},{"id":"2212.09689","title":"Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor","created":"2022-12-19","cited_by_count":397},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"2305.15717","title":"The False Promise of Imitating Proprietary LLMs","created":"2023-05-25","cited_by_count":263},{"id":"1911.03437","title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","created":"2019-11-08","cited_by_count":254},{"id":"2012.15828","title":"MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers","created":"2020-12-31","cited_by_count":245},{"id":"2304.14402","title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","created":"2023-04-27","cited_by_count":124},{"id":"2204.01171","title":"Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation","created":"2022-04-03","cited_by_count":108},{"id":"1905.13472","title":"Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness","created":"2019-05-31","cited_by_count":104},{"id":"1811.02549","title":"Language GANs Falling Short","created":"2018-11-06","cited_by_count":97},{"id":"1902.02186","title":"Distilling Policy Distillation","created":"2019-02-06","cited_by_count":84},{"id":"1511.05101","title":"How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?","created":"2015-11-16","cited_by_count":78},{"id":"2011.00593","title":"MixKD: Towards Efficient Distillation of Large-scale Language Models","created":"2020-11-01","cited_by_count":65},{"id":"2009.07839","title":"Text Generation by Learning from Demonstrations","created":"2020-09-16","cited_by_count":64},{"id":"2102.06483","title":"Scalable Bayesian Inverse Reinforcement Learning","created":"2021-02-12","cited_by_count":56},{"id":"1709.02349","title":"A Deep Reinforcement Learning Chatbot","created":"2017-09-07","cited_by_count":36},{"id":"2302.13344","title":"Tailoring Language Generation Models under Total Variation Distance","created":"2023-02-26","cited_by_count":27},{"id":"2004.12817","title":"LightPAFF: A Two-Stage Distillation Framework for Pre-training and Fine-tuning","created":"2020-04-27","cited_by_count":25},{"id":"2305.05010","title":"Do Not Blindly Imitate the Teacher: Using Perturbed Loss for Knowledge Distillation","created":"2023-05-08","cited_by_count":25},{"id":"2208.05642","title":"Self-Knowledge Distillation via Dropout","created":"2022-08-11","cited_by_count":18},{"id":"2108.04763","title":"Imitation Learning by Reinforcement Learning","created":"2021-08-10","cited_by_count":17},{"id":"1709.01846","title":"Symmetric Variational Autoencoder and Connections to Adversarial Learning","created":"2017-09-06","cited_by_count":14},{"id":"2210.08708","title":"Teacher Forcing Recovers Reward Functions for Text Generation","created":"2022-10-17","cited_by_count":11},{"id":"2010.05994","title":"Improving Text Generation with Student-Forcing Optimal Transport","created":"2020-10-12","cited_by_count":8}],"next_cursor":null}