{"list":"other","total":87,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"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":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"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":"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":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"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":"1606.06031","title":"The LAMBADA dataset: Word prediction requiring a broad discourse context","created":"2016-06-20","cited_by_count":992},{"id":"2306.13649","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","created":"2023-06-23","cited_by_count":939},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"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":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"id":"1911.02150","title":"Fast Transformer Decoding: One Write-Head is All You Need","created":"2019-11-06","cited_by_count":717},{"id":"1906.00300","title":"Latent Retrieval for Weakly Supervised Open Domain Question Answering","created":"2019-06-01","cited_by_count":695},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"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":"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":"2003.05002","title":"TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages","created":"2020-03-10","cited_by_count":488},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467},{"id":"1604.01696","title":"A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories","created":"2016-04-06","cited_by_count":417},{"id":"2106.13822","title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages","created":"2021-06-25","cited_by_count":347},{"id":"1803.00942","title":"Not All Samples Are Created Equal: Deep Learning with Importance Sampling","created":"2018-03-02","cited_by_count":328},{"id":"2303.09540","title":"SemDeDup: Data-efficient learning at web-scale through semantic deduplication","created":"2023-03-16","cited_by_count":303},{"id":"2012.09816","title":"Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning","created":"2020-12-17","cited_by_count":297},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284},{"id":"2301.12726","title":"Specializing Smaller Language Models towards Multi-Step Reasoning","created":"2023-01-30","cited_by_count":251},{"id":"2206.07137","title":"Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt","created":"2022-06-14","cited_by_count":236},{"id":"2402.16827","title":"A Survey on Data Selection for Language Models","created":"2024-02-26","cited_by_count":236},{"id":"1905.11604","title":"SGD on Neural Networks Learns Functions of Increasing Complexity","created":"2019-05-28","cited_by_count":204},{"id":"1810.12885","title":"ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension","created":"2018-10-30","cited_by_count":200},{"id":"2203.17189","title":"Scaling Up Models and Data with $\\texttt{t5x}$ and $\\texttt{seqio}$","created":"2022-03-31","cited_by_count":187},{"id":"2002.05715","title":"Self-Distillation Amplifies Regularization in Hilbert Space","created":"2020-02-13","cited_by_count":173},{"id":"2105.13093","title":"Towards Understanding Knowledge Distillation","created":"2021-05-27","cited_by_count":158},{"id":"2010.03093","title":"WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization","created":"2020-10-07","cited_by_count":154},{"id":"2308.12284","title":"D4: Improving LLM Pretraining via Document De-Duplication and Diversification","created":"2023-08-23","cited_by_count":150},{"id":"2310.03094","title":"Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning","created":"2023-10-04","cited_by_count":143},{"id":"2404.07965","title":"Rho-1: Not All Tokens Are What You Need","created":"2024-04-11","cited_by_count":133},{"id":"2404.10136","title":"Language Model Cascades: Token-level uncertainty and beyond","created":"2024-04-15","cited_by_count":121},{"id":"2307.15190","title":"f-Divergence Minimization for Sequence-Level Knowledge Distillation","created":"2023-07-27","cited_by_count":114},{"id":"2405.20541","title":"Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models","created":"2024-05-30","cited_by_count":84},{"id":"2310.12962","title":"An Emulator for Fine-Tuning Large Language Models using Small Language Models","created":"2023-10-19","cited_by_count":61},{"id":"2305.09828","title":"Mimetic Initialization of Self-Attention Layers","created":"2023-05-16","cited_by_count":54},{"id":"2312.17173","title":"Non-Vacuous Generalization Bounds for Large Language Models","created":"2023-12-28","cited_by_count":53},{"id":"2211.11567","title":"Neural networks trained with SGD learn distributions of increasing complexity","created":"2022-11-21","cited_by_count":50},{"id":"2010.12562","title":"On the Transformer Growth for Progressive BERT Training","created":"2020-10-23","cited_by_count":49},{"id":"2403.07384","title":"SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models","created":"2024-03-12","cited_by_count":44},{"id":"2105.13880","title":"Knowledge Inheritance for Pre-trained Language Models","created":"2021-05-28","cited_by_count":38},{"id":"2402.11148","title":"Knowledge Distillation Based on Transformed Teacher Matching","created":"2024-02-17","cited_by_count":37},{"id":"2410.02724","title":"Large Language Models as Markov Chains","created":"2024-10-03","cited_by_count":35},{"id":"2104.09732","title":"Knowledge Distillation as Semiparametric Inference","created":"2021-04-20","cited_by_count":29},{"id":"2310.14029","title":"LLM-Prop: Predicting Physical And Electronic Properties Of Crystalline Solids From Their Text Descriptions","created":"2023-10-21","cited_by_count":29},{"id":"2409.12903","title":"Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization","created":"2024-09-19","cited_by_count":29},{"id":"2407.18158","title":"Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models","created":"2024-07-25","cited_by_count":25},{"id":"2310.07999","title":"LEMON: Lossless model expansion","created":"2023-10-12","cited_by_count":23},{"id":"2203.02485","title":"Better Supervisory Signals by Observing Learning Paths","created":"2022-03-04","cited_by_count":21},{"id":"2301.12245","title":"Supervision Complexity and its Role in Knowledge Distillation","created":"2023-01-28","cited_by_count":19},{"id":"2006.11653","title":"Towards Understanding Label Smoothing","created":"2020-06-20","cited_by_count":17},{"id":"2301.12923","title":"On student-teacher deviations in distillation: does it pay to disobey?","created":"2023-01-30","cited_by_count":16},{"id":"1609.06385","title":"Multiclass Classification Calibration Functions","created":"2016-09-20","cited_by_count":13},{"id":"2305.17581","title":"Knowledge Distillation Performs Partial Variance Reduction","created":"2023-05-27","cited_by_count":11},{"id":"2102.06849","title":"Distilling Double Descent","created":"2021-02-13","cited_by_count":7}],"next_cursor":null}