{"list":"other","total":83,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"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":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"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":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"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":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"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":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"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":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"2305.13245","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","created":"2023-05-22","cited_by_count":1346},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"2305.14233","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","created":"2023-05-23","cited_by_count":839},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2304.07327","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","created":"2023-04-14","cited_by_count":721},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713},{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642},{"id":"2401.02385","title":"TinyLlama: An Open-Source Small Language Model","created":"2024-01-04","cited_by_count":618},{"id":"2306.11644","title":"Textbooks Are All You Need","created":"2023-06-20","cited_by_count":569},{"id":"1911.00359","title":"CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data","created":"2019-11-01","cited_by_count":548},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535},{"id":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530},{"id":"1910.09700","title":"Quantifying the Carbon Emissions of Machine Learning","created":"2019-10-21","cited_by_count":521},{"id":"2110.02861","title":"8-bit Optimizers via Block-wise Quantization","created":"2021-10-06","cited_by_count":403},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403},{"id":"1911.03894","title":"CamemBERT: a Tasty French Language Model","created":"2019-11-10","cited_by_count":368},{"id":"2211.15533","title":"The Stack: 3 TB of permissively licensed source code","created":"2022-11-20","cited_by_count":359},{"id":"2304.08177","title":"Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca","created":"2023-04-17","cited_by_count":305},{"id":"1909.00277","title":"Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning","created":"2019-08-31","cited_by_count":285},{"id":"2211.02001","title":"Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model","created":"2022-11-03","cited_by_count":265},{"id":"2309.09400","title":"CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages","created":"2023-09-17","cited_by_count":174},{"id":"2204.06487","title":"Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning","created":"2022-04-13","cited_by_count":149},{"id":"2303.03915","title":"The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset","created":"2023-03-07","cited_by_count":148},{"id":"2201.06642","title":"Towards a Cleaner Document-Oriented Multilingual Crawled Corpus","created":"2022-01-17","cited_by_count":143},{"id":"2204.07580","title":"mGPT: Few-Shot Learners Go Multilingual","created":"2022-04-15","cited_by_count":142},{"id":"2006.06202","title":"A Monolingual Approach to Contextualized Word Embeddings for Mid-Resource Languages","created":"2020-06-11","cited_by_count":131},{"id":"2304.03208","title":"Cerebras-GPT: Open Compute-Optimal Language Models Trained on the Cerebras Wafer-Scale Cluster","created":"2023-04-06","cited_by_count":109},{"id":"2401.01055","title":"LLaMA Beyond English: An Empirical Study on Language Capability Transfer","created":"2024-01-02","cited_by_count":95},{"id":"2305.13230","title":"To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis","created":"2023-05-22","cited_by_count":92},{"id":"2305.15011","title":"Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank Adaptation","created":"2023-05-24","cited_by_count":81},{"id":"2305.14705","title":"Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models","created":"2023-05-24","cited_by_count":65},{"id":"2109.05472","title":"Compute and Energy Consumption Trends in Deep Learning Inference","created":"2021-09-12","cited_by_count":61},{"id":"2012.15520","title":"AraGPT2: Pre-Trained Transformer for Arabic Language Generation","created":"2020-12-31","cited_by_count":55},{"id":"2012.02110","title":"GottBERT: a pure German Language Model","created":"2020-12-03","cited_by_count":49},{"id":"2306.11372","title":"Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts","created":"2023-06-20","cited_by_count":45},{"id":"1911.08354","title":"Energy Usage Reports: Environmental awareness as part of algorithmic accountability","created":"2019-11-19","cited_by_count":44},{"id":"2107.07253","title":"MarIA: Spanish Language Models","created":"2021-07-15","cited_by_count":36},{"id":"1909.04761","title":"MultiFiT: Efficient Multi-lingual Language Model Fine-tuning","created":"2019-09-10","cited_by_count":31},{"id":"2308.11878","title":"Cabrita: closing the gap for foreign languages","created":"2023-08-23","cited_by_count":25},{"id":"2305.06721","title":"Advancing Neural Encoding of Portuguese with Transformer Albertina PT-*","created":"2023-05-11","cited_by_count":24},{"id":"2306.02254","title":"A Technical Report for Polyglot-Ko: Open-Source Large-Scale Korean Language Models","created":"2023-06-04","cited_by_count":22},{"id":"2103.14972","title":"HateBR: A Large Expert Annotated Corpus of Brazilian Instagram Comments for Offensive Language and Hate Speech Detection","created":"2021-03-27","cited_by_count":15},{"id":"2401.02909","title":"Introducing Bode: A Fine-Tuned Large Language Model for Portuguese Prompt-Based Task","created":"2024-01-05","cited_by_count":12},{"id":"2104.07483","title":"IndT5: A Text-to-Text Transformer for 10 Indigenous Languages","created":"2021-04-04","cited_by_count":10},{"id":"2312.14862","title":"YAYI 2: Multilingual Open-Source Large Language Models","created":"2023-12-22","cited_by_count":6}],"next_cursor":null}