{"list":"other","total":64,"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":"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":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"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":"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":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1903.10676","title":"SciBERT: A Pretrained Language Model for Scientific Text","created":"2019-03-26","cited_by_count":1414},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868},{"id":"2401.06066","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","created":"2024-01-11","cited_by_count":867},{"id":"2305.14233","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","created":"2023-05-23","cited_by_count":839},{"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":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","created":"2024-04-09","cited_by_count":723},{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623},{"id":"2401.02385","title":"TinyLlama: An Open-Source Small Language Model","created":"2024-01-04","cited_by_count":618},{"id":"2306.04751","title":"How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources","created":"2023-06-07","cited_by_count":408},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403},{"id":"2401.15947","title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","created":"2024-01-29","cited_by_count":300},{"id":"2311.16079","title":"MEDITRON-70B: Scaling Medical Pretraining for Large Language Models","created":"2023-11-27","cited_by_count":274},{"id":"2402.16827","title":"A Survey on Data Selection for Language Models","created":"2024-02-26","cited_by_count":236},{"id":"2312.00886","title":"Nash Learning from Human Feedback","created":"2023-12-01","cited_by_count":224},{"id":"2306.09479","title":"Inverse Scaling: When Bigger Isn't Better","created":"2023-06-15","cited_by_count":207},{"id":"2402.17733","title":"Tower: An Open Multilingual Large Language Model for Translation-Related Tasks","created":"2024-02-27","cited_by_count":206},{"id":"2403.11549","title":"Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters","created":"2024-03-18","cited_by_count":199},{"id":"2301.03988","title":"SantaCoder: don't reach for the stars!","created":"2023-01-09","cited_by_count":170},{"id":"2403.03883","title":"SaulLM-7B: A pioneering Large Language Model for Law","created":"2024-03-06","cited_by_count":142},{"id":"2207.00220","title":"Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset","created":"2022-07-01","cited_by_count":113},{"id":"2403.08635","title":"Human Alignment of Large Language Models through Online Preference Optimisation","created":"2024-03-13","cited_by_count":91},{"id":"2403.18421","title":"BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text","created":"2024-03-27","cited_by_count":86},{"id":"2305.07017","title":"An Inverse Scaling Law for CLIP Training","created":"2023-05-11","cited_by_count":77},{"id":"2309.10818","title":"SlimPajama-DC: Understanding Data Combinations for LLM Training","created":"2023-09-19","cited_by_count":72},{"id":"2305.18438","title":"Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism","created":"2023-05-29","cited_by_count":69},{"id":"2404.12387","title":"Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models","created":"2024-04-18","cited_by_count":67},{"id":"2306.02069","title":"MultiLegalPile: A 689GB Multilingual Legal Corpus","created":"2023-06-03","cited_by_count":60},{"id":"2401.04081","title":"MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts","created":"2024-01-08","cited_by_count":60},{"id":"2112.07869","title":"Fine-Tuning Large Neural Language Models for Biomedical Natural Language Processing","created":"2021-12-15","cited_by_count":57},{"id":"2402.00786","title":"CroissantLLM: A Truly Bilingual French-English Language Model","created":"2024-02-01","cited_by_count":53},{"id":"1810.02263","title":"Convergence and Dynamical Behavior of the ADAM Algorithm for Non-Convex Stochastic Optimization","created":"2018-10-04","cited_by_count":49},{"id":"2310.13448","title":"Steering Large Language Models for Machine Translation with Finetuning and In-Context Learning","created":"2023-10-20","cited_by_count":49},{"id":"2209.06049","title":"Pre-trained Language Models for the Legal Domain: A Case Study on Indian Law","created":"2022-09-13","cited_by_count":39},{"id":"2106.13474","title":"Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains","created":"2021-06-25","cited_by_count":36},{"id":"2402.16819","title":"Nemotron-4 15B Technical Report","created":"2024-02-26","cited_by_count":36},{"id":"2212.09171","title":"Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Data","created":"2022-12-18","cited_by_count":21},{"id":"2103.12711","title":"A Pseudo-Metric between Probability Distributions based on Depth-Trimmed Regions","created":"2021-03-23","cited_by_count":17},{"id":"2209.06120","title":"LegalBench: Prototyping a Collaborative Benchmark for Legal Reasoning","created":"2022-09-13","cited_by_count":17},{"id":"2302.09852","title":"Unsupervised Layer-wise Score Aggregation for Textual OOD Detection","created":"2023-02-20","cited_by_count":15},{"id":"2211.17135","title":"BudgetLongformer: Can we Cheaply Pretrain a SotA Legal Language Model From Scratch?","created":"2022-11-30","cited_by_count":13},{"id":"2110.12201","title":"Spanish Legalese Language Model and Corpora","created":"2021-10-23","cited_by_count":11},{"id":"2310.14103","title":"Revisiting Instruction Fine-tuned Model Evaluation to Guide Industrial Applications","created":"2023-10-21","cited_by_count":11},{"id":"2404.12349","title":"Evaluating AI for Law: Bridging the Gap with Open-Source Solutions","created":"2024-04-18","cited_by_count":11},{"id":"2404.02127","title":"LawInstruct: A Resource for Studying Language Model Adaptation to the Legal Domain","created":"2024-04-02","cited_by_count":10},{"id":"2404.15894","title":"Assessing The Potential Of Mid-Sized Language Models For Clinical QA","created":"2024-04-24","cited_by_count":4}],"next_cursor":null}