{"list":"other","total":105,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"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":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"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":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"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":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1606.06031","title":"The LAMBADA dataset: Word prediction requiring a broad discourse context","created":"2016-06-20","cited_by_count":992},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"2306.01116","title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","created":"2023-06-01","cited_by_count":763},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"1808.07042","title":"CoQA: A Conversational Question Answering Challenge","created":"2018-08-21","cited_by_count":683},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613},{"id":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"2306.11644","title":"Textbooks Are All You Need","created":"2023-06-20","cited_by_count":569},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","created":"2023-04-28","cited_by_count":523},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492},{"id":"2402.00159","title":"Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research","created":"2024-01-31","cited_by_count":483},{"id":"1804.09301","title":"Gender Bias in Coreference Resolution","created":"2018-04-25","cited_by_count":442},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295},{"id":"2203.03466","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","created":"2022-03-07","cited_by_count":288},{"id":"1608.05859","title":"Using the Output Embedding to Improve Language Models","created":"2016-08-20","cited_by_count":272},{"id":"2102.01293","title":"Scaling Laws for Transfer","created":"2021-02-02","cited_by_count":272},{"id":"2402.16827","title":"A Survey on Data Selection for Language Models","created":"2024-02-26","cited_by_count":236},{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233},{"id":"2010.15875","title":"Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning","created":"2020-10-29","cited_by_count":216},{"id":"1909.12673","title":"A Constructive Prediction of the Generalization Error Across Scales","created":"2019-09-27","cited_by_count":210},{"id":"2011.14522","title":"Feature Learning in Infinite-Width Neural Networks","created":"2020-11-30","cited_by_count":190},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189},{"id":"2309.14322","title":"Small-scale proxies for large-scale Transformer training instabilities","created":"2023-09-25","cited_by_count":183},{"id":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177},{"id":"2112.10684","title":"Efficient Large Scale Language Modeling with Mixtures of Experts","created":"2021-12-20","cited_by_count":175},{"id":"2301.03988","title":"SantaCoder: don't reach for the stars!","created":"2023-01-09","cited_by_count":170},{"id":"2401.00448","title":"Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws","created":"2023-12-31","cited_by_count":159},{"id":"2209.06640","title":"Revisiting Neural Scaling Laws in Language and Vision","created":"2022-09-13","cited_by_count":132},{"id":"1911.12011","title":"JEC-QA: A Legal-Domain Question Answering Dataset","created":"2019-11-27","cited_by_count":116},{"id":"2109.07740","title":"Scaling Laws for Neural Machine Translation","created":"2021-09-16","cited_by_count":111},{"id":"2210.14891","title":"Broken Neural Scaling Laws","created":"2022-10-26","cited_by_count":109},{"id":"2109.10686","title":"Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers","created":"2021-09-22","cited_by_count":106},{"id":"2110.02095","title":"Exploring the Limits of Large Scale Pre-training","created":"2021-10-05","cited_by_count":104},{"id":"2207.10551","title":"Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?","created":"2022-07-21","cited_by_count":103},{"id":"1611.01462","title":"Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling","created":"2016-11-04","cited_by_count":92},{"id":"2210.15424","title":"What Language Model to Train if You Have One Million GPU Hours?","created":"2022-10-27","cited_by_count":92},{"id":"2310.16787","title":"The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI","created":"2023-10-25","cited_by_count":73},{"id":"1908.11365","title":"Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention","created":"2019-08-29","cited_by_count":59},{"id":"2202.01994","title":"Data Scaling Laws in NMT: The Effect of Noise and Architecture","created":"2022-02-04","cited_by_count":55},{"id":"2312.10523","title":"Paloma: A Benchmark for Evaluating Language Model Fit","created":"2023-12-16","cited_by_count":54},{"id":"2004.10802","title":"A Neural Scaling Law from the Dimension of the Data Manifold","created":"2020-04-22","cited_by_count":52},{"id":"2311.05640","title":"FinGPT: Large Generative Models for a Small Language","created":"2023-11-03","cited_by_count":49},{"id":"2402.04177","title":"Scaling Laws for Downstream Task Performance of Large Language Models","created":"2024-02-06","cited_by_count":49},{"id":"2108.00648","title":"From LSAT: The Progress and Challenges of Complex Reasoning","created":"2021-08-02","cited_by_count":43}],"next_cursor":"100"}