{"list":"other","total":66,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"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":"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":"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":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"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":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"1811.11682","title":"Experience Replay for Continual Learning","created":"2018-11-28","cited_by_count":1095},{"id":"2004.07211","title":"Dark Experience for General Continual Learning: a Strong, Simple Baseline","created":"2020-04-15","cited_by_count":911},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"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":"2401.02385","title":"TinyLlama: An Open-Source Small Language Model","created":"2024-01-04","cited_by_count":618},{"id":"2203.14371","title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","created":"2022-03-27","cited_by_count":543},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"2302.06476","title":"Is ChatGPT a General-Purpose Natural Language Processing Task Solver?","created":"2023-02-08","cited_by_count":488},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399},{"id":"2312.15685","title":"What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning","created":"2023-12-25","cited_by_count":364},{"id":"2402.10373","title":"BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains","created":"2024-02-15","cited_by_count":301},{"id":"2304.08247","title":"MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data","created":"2023-04-14","cited_by_count":286},{"id":"2311.16079","title":"MEDITRON-70B: Scaling Medical Pretraining for Large Language Models","created":"2023-11-27","cited_by_count":274},{"id":"2104.05025","title":"New Insights on Reducing Abrupt Representation Change in Online Continual Learning","created":"2021-04-11","cited_by_count":219},{"id":"2305.17100","title":"BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks","created":"2023-05-26","cited_by_count":201},{"id":"2402.10171","title":"Data Engineering for Scaling Language Models to 128K Context","created":"2024-02-15","cited_by_count":186},{"id":"2205.10487","title":"Scaling Laws and Interpretability of Learning from Repeated Data","created":"2022-05-21","cited_by_count":152},{"id":"2308.04014","title":"Continual Pre-Training of Large Language Models: How to (re)warm your model?","created":"2023-08-08","cited_by_count":137},{"id":"2305.18703","title":"Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey","created":"2023-05-30","cited_by_count":135},{"id":"2404.07965","title":"Rho-1: Not All Tokens Are What You Need","created":"2024-04-11","cited_by_count":133},{"id":"2403.08763","title":"Simple and Scalable Strategies to Continually Pre-train Large Language Models","created":"2024-03-13","cited_by_count":127},{"id":"2402.11187","title":"LaCo: Large Language Model Pruning via Layer Collapse","created":"2024-02-17","cited_by_count":126},{"id":"2110.08534","title":"Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora","created":"2021-10-16","cited_by_count":115},{"id":"2010.05595","title":"Rethinking Experience Replay: a Bag of Tricks for Continual Learning","created":"2020-10-12","cited_by_count":94},{"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":"2304.14454","title":"PMC-LLaMA: Towards Building Open-source Language Models for Medicine","created":"2023-04-27","cited_by_count":88},{"id":"2309.10818","title":"SlimPajama-DC: Understanding Data Combinations for LLM Training","created":"2023-09-19","cited_by_count":72},{"id":"2305.12281","title":"Lifelong Language Pretraining with Distribution-Specialized Experts","created":"2023-05-20","cited_by_count":66},{"id":"2402.17400","title":"Investigating Continual Pretraining in Large Language Models: Insights and Implications","created":"2024-02-27","cited_by_count":57},{"id":"2205.13452","title":"Continual evaluation for lifelong learning: Identifying the stability gap","created":"2022-05-26","cited_by_count":56},{"id":"2402.12847","title":"Instruction-tuned Language Models are Better Knowledge Learners","created":"2024-02-20","cited_by_count":55},{"id":"2305.15062","title":"Lawyer LLaMA Technical Report","created":"2023-05-24","cited_by_count":54},{"id":"2405.03000","title":"MedAdapter: Efficient Test-Time Adaptation of Large Language Models towards Medical Reasoning","created":"2024-05-05","cited_by_count":36},{"id":"2210.05549","title":"Continual Training of Language Models for Few-Shot Learning","created":"2022-10-11","cited_by_count":33},{"id":"2311.01767","title":"PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completion","created":"2023-11-03","cited_by_count":30},{"id":"2402.16671","title":"StructLM: Towards Building Generalist Models for Structured Knowledge Grounding","created":"2024-02-26","cited_by_count":29},{"id":"2402.07625","title":"Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts","created":"2024-02-12","cited_by_count":27},{"id":"2301.08986","title":"Adapting a Language Model While Preserving its General Knowledge","created":"2023-01-21","cited_by_count":23},{"id":"2401.01600","title":"PLLaMa: An Open-source Large Language Model for Plant Science","created":"2024-01-03","cited_by_count":22},{"id":"2405.01886","title":"Aloe: A Family of Fine-tuned Open Healthcare LLMs","created":"2024-05-03","cited_by_count":20},{"id":"2210.14814","title":"BioNLI: Generating a Biomedical NLI Dataset Using Lexico-semantic Constraints for Adversarial Examples","created":"2022-10-26","cited_by_count":15},{"id":"2306.01904","title":"Overcoming the Stability Gap in Continual Learning","created":"2023-06-02","cited_by_count":13},{"id":"2210.10258","title":"Continued Pretraining for Better Zero- and Few-Shot Promptability","created":"2022-10-19","cited_by_count":10}],"next_cursor":null}