{"list":"other","total":51,"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"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":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853},{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"id":"1907.09693","title":"A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection","created":"2019-07-23","cited_by_count":374},{"id":"2305.17126","title":"Large Language Models as Tool Makers","created":"2023-05-26","cited_by_count":303},{"id":"2110.01691","title":"AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts","created":"2021-10-04","cited_by_count":268},{"id":"2106.05237","title":"Knowledge distillation: A good teacher is patient and consistent","created":"2021-06-09","cited_by_count":259},{"id":"1803.06535","title":"Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer","created":"2018-03-17","cited_by_count":211},{"id":"2108.13487","title":"Want To Reduce Labeling Cost? GPT-3 Can Help","created":"2021-08-30","cited_by_count":196},{"id":"2210.02441","title":"Ask Me Anything: A simple strategy for prompting language models","created":"2022-10-05","cited_by_count":155},{"id":"1903.12136","title":"Distilling Task-Specific Knowledge from BERT into Simple Neural Networks","created":"2019-03-28","cited_by_count":153},{"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":"2304.14402","title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","created":"2023-04-27","cited_by_count":124},{"id":"2109.03910","title":"A Recipe For Arbitrary Text Style Transfer with Large Language Models","created":"2021-09-08","cited_by_count":107},{"id":"2207.10342","title":"Language Model Cascades","created":"2022-07-21","cited_by_count":107},{"id":"1702.04066","title":"JFLEG: A Fluency Corpus and Benchmark for Grammatical Error Correction","created":"2017-02-14","cited_by_count":97},{"id":"2206.02369","title":"Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation","created":"2022-06-06","cited_by_count":94},{"id":"2208.11663","title":"PEER: A Collaborative Language Model","created":"2022-08-24","cited_by_count":86},{"id":"1908.00080","title":"Machine Learning at the Network Edge: A Survey","created":"2019-07-31","cited_by_count":84},{"id":"2305.15685","title":"RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting","created":"2023-05-25","cited_by_count":67},{"id":"2205.02318","title":"Language Models in the Loop: Incorporating Prompting into Weak Supervision","created":"2022-05-04","cited_by_count":52},{"id":"2012.14682","title":"CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade","created":"2020-12-29","cited_by_count":47},{"id":"2304.11267","title":"Speed Is All You Need: On-Device Acceleration of Large Diffusion Models via GPU-Aware Optimizations","created":"2023-04-21","cited_by_count":45},{"id":"2106.02757","title":"Heuristic-Guided Reinforcement Learning","created":"2021-06-05","cited_by_count":42},{"id":"2010.03802","title":"TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restyling","created":"2020-10-08","cited_by_count":40},{"id":"2005.07522","title":"Parallel Data Augmentation for Formality Style Transfer","created":"2020-05-14","cited_by_count":39},{"id":"2112.08634","title":"FRUIT: Faithfully Reflecting Updated Information in Text","created":"2021-12-16","cited_by_count":39},{"id":"2205.12209","title":"EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Start","created":"2022-05-24","cited_by_count":35},{"id":"2010.12826","title":"Text Editing by Command","created":"2020-10-24","cited_by_count":33},{"id":"2209.13331","title":"EditEval: An Instruction-Based Benchmark for Text Improvements","created":"2022-09-27","cited_by_count":30},{"id":"2007.02244","title":"Unsupervised Paraphrasing via Deep Reinforcement Learning","created":"2020-07-05","cited_by_count":25},{"id":"2206.07043","title":"Text Generation with Text-Editing Models","created":"2022-06-14","cited_by_count":21},{"id":"1908.06809","title":"Style Transfer for Texts: Retrain, Report Errors, Compare with Rewrites","created":"2019-08-19","cited_by_count":20},{"id":"2210.06711","title":"Weighted Distillation with Unlabeled Examples","created":"2022-10-13","cited_by_count":13},{"id":"2305.01645","title":"Distill or Annotate? Cost-Efficient Fine-Tuning of Compact Models","created":"2023-05-02","cited_by_count":11}],"next_cursor":null}