{"total":80,"rows":[{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984,"area":null},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786,"area":null},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939,"area":null},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827,"area":null},{"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,"area":null},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535,"area":null},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403,"area":null},{"id":"2305.19466","title":"The Impact of Positional Encoding on Length Generalization in Transformers","created":"2023-05-31","cited_by_count":327,"area":null},{"id":"2211.02001","title":"Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model","created":"2022-11-03","cited_by_count":265,"area":null},{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233,"area":null},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189,"area":null},{"id":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177,"area":null},{"id":"2304.11158","title":"Emergent and Predictable Memorization in Large Language Models","created":"2023-04-21","cited_by_count":148,"area":null},{"id":"2312.03718","title":"Large Language Models in Law: A Survey","created":"2023-11-26","cited_by_count":128,"area":null},{"id":"2303.03369","title":"Multimodal Prompting with Missing Modalities for Visual Recognition","created":"2023-03-06","cited_by_count":121,"area":null},{"id":"2407.13623","title":"Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies","created":"2024-07-18","cited_by_count":118,"area":null},{"id":"2212.10846","title":"From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models","created":"2022-12-21","cited_by_count":115,"area":null},{"id":"2403.08540","title":"Language models scale reliably with over-training and on downstream tasks","created":"2024-03-13","cited_by_count":113,"area":null},{"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,"area":null},{"id":"2409.16235","title":"EuroLLM: Multilingual Language Models for Europe","created":"2024-09-24","cited_by_count":106,"area":null},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2307.16376","title":"When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities","created":"2023-07-31","cited_by_count":90,"area":null},{"id":"2212.09803","title":"Training Trajectories of Language Models Across Scales","created":"2022-12-19","cited_by_count":81,"area":null},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"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,"area":null},{"id":"2305.05862","title":"Are ChatGPT and GPT-4 General-Purpose Solvers for Financial Text Analytics? A Study on Several Typical Tasks","created":"2023-05-10","cited_by_count":59,"area":null},{"id":"2312.16903","title":"Spike No More: Stabilizing the Pre-training of Large Language Models","created":"2023-12-28","cited_by_count":52,"area":null},{"id":"2401.06199","title":"xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein","created":"2024-01-11","cited_by_count":50,"area":null},{"id":"2311.05640","title":"FinGPT: Large Generative Models for a Small Language","created":"2023-11-03","cited_by_count":49,"area":null},{"id":"2407.14933","title":"Consent in Crisis: The Rapid Decline of the AI Data Commons","created":"2024-07-20","cited_by_count":46,"area":null},{"id":"2410.01623","title":"Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?","created":"2024-10-02","cited_by_count":43,"area":null},{"id":"2312.12683","title":"Turning English-centric LLMs Into Polyglots: How Much Multilinguality Is Needed?","created":"2023-12-20","cited_by_count":39,"area":null},{"id":"2311.00913","title":"Self-Influence Guided Data Reweighting for Language Model Pre-training","created":"2023-11-02","cited_by_count":37,"area":null},{"id":"2412.13795","title":"Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN","created":"2024-12-18","cited_by_count":37,"area":null},{"id":"2401.05749","title":"A Shocking Amount of the Web is Machine Translated: Insights from Multi-Way Parallelism","created":"2024-01-11","cited_by_count":35,"area":null},{"id":"2501.06842","title":"SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training","created":"2025-01-12","cited_by_count":28,"area":null},{"id":"2301.09626","title":"Efficient Language Model Training through Cross-Lingual and Progressive Transfer Learning","created":"2023-01-23","cited_by_count":26,"area":null},{"id":"2304.03589","title":"On Efficient Training of Large-Scale Deep Learning Models: A Literature Review","created":"2023-04-07","cited_by_count":26,"area":null},{"id":"2305.13571","title":"Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings","created":"2023-05-23","cited_by_count":23,"area":null},{"id":"2403.19347","title":"Breaking the Length Barrier: LLM-Enhanced CTR Prediction in Long Textual User Behaviors","created":"2024-03-28","cited_by_count":23,"area":null},{"id":"2510.22037","title":"ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality","created":"2025-10-24","cited_by_count":22,"area":null},{"id":"2406.04327","title":"Causal Estimation of Memorisation Profiles","created":"2024-06-06","cited_by_count":20,"area":null},{"id":"2309.11568","title":"BTLM-3B-8K: 7B Parameter Performance in a 3B Parameter Model","created":"2023-09-20","cited_by_count":19,"area":null},{"id":"2410.06558","title":"Deep Correlated Prompting for Visual Recognition with Missing Modalities","created":"2024-10-09","cited_by_count":18,"area":null},{"id":"2502.00641","title":"Evaluating Small Language Models for News Summarization: Implications and Factors Influencing Performance","created":"2025-02-02","cited_by_count":12,"area":null},{"id":"2506.07597","title":"Instructing Large Language Models for Low-Resource Languages: A Systematic Study for Basque","created":"2025-06-09","cited_by_count":12,"area":null},{"id":"2405.13816","title":"Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learners","created":"2024-05-22","cited_by_count":11,"area":null},{"id":"2406.16508","title":"Large Vocabulary Size Improves Large Language Models","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2506.03101","title":"Beyond Text Compression: Evaluating Tokenizers Across Scales","created":"2025-06-03","cited_by_count":11,"area":null},{"id":"2601.07220","title":"The Roots of Performance Disparity in Multilingual Language Models: Intrinsic Modeling Difficulty or Design Choices?","created":"2026-01-12","cited_by_count":11,"area":null},{"id":"2303.04715","title":"Extending the Pre-Training of BLOOM for Improved Support of Traditional Chinese: Models, Methods and Results","created":"2023-03-08","cited_by_count":10,"area":null},{"id":"2408.06273","title":"FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data","created":"2024-08-12","cited_by_count":10,"area":null},{"id":"2502.15392","title":"Chitrarth: Bridging Vision and Language for a Billion People","created":"2025-02-21","cited_by_count":10,"area":null},{"id":"2505.14824","title":"Tracing Multilingual Factual Knowledge Acquisition in Pretraining","created":"2025-05-20","cited_by_count":10,"area":null},{"id":"2412.17743","title":"YuLan-Mini: An Open Data-efficient Language Model","created":"2024-12-23","cited_by_count":7,"area":null},{"id":"2305.07280","title":"Harvesting Event Schemas from Large Language Models","created":"2023-05-12","cited_by_count":6,"area":null},{"id":"2310.09141","title":"PuoBERTa: Training and evaluation of a curated language model for Setswana","created":"2023-10-13","cited_by_count":6,"area":null},{"id":"2409.07787","title":"Stable Language Model Pre-training by Reducing Embedding Variability","created":"2024-09-12","cited_by_count":6,"area":null},{"id":"2501.00659","title":"Why Are Positional Encodings Nonessential for Deep Autoregressive Transformers? Revisiting a Petroglyph","created":"2024-12-31","cited_by_count":6,"area":null},{"id":"2310.14248","title":"From Static to Dynamic: A Continual Learning Framework for Large Language Models","created":"2023-10-22","cited_by_count":4,"area":null},{"id":"2401.08089","title":"A Study on Training and Developing Large Language Models for Behavior Tree Generation","created":"2024-01-16","cited_by_count":4,"area":null},{"id":"2404.04530","title":"A Morphology-Based Investigation of Positional Encodings","created":"2024-04-06","cited_by_count":4,"area":null},{"id":"2410.05052","title":"Initialization of Large Language Models via Reparameterization to Mitigate Loss Spikes","created":"2024-10-07","cited_by_count":4,"area":null},{"id":"2305.02440","title":"Cheaply Evaluating Inference Efficiency Metrics for Autoregressive Transformer APIs","created":"2023-05-03","cited_by_count":3,"area":null},{"id":"2404.07580","title":"Multi-rater Prompting for Ambiguous Medical Image Segmentation","created":"2024-04-11","cited_by_count":3,"area":null},{"id":"2305.11991","title":"Evaluation of medium-large Language Models at zero-shot closed book generative question answering","created":"2023-05-19","cited_by_count":2,"area":null},{"id":"2505.01110","title":"MateICL: Mitigating Attention Dispersion in Large-Scale In-Context Learning","created":"2025-05-02","cited_by_count":2,"area":null},{"id":"2502.05765","title":"Privacy-Preserving Dataset Combination","created":"2025-02-09","cited_by_count":1,"area":null},{"id":"2507.06464","title":"SoftSignSGD(S3): An Enhanced Optimizer for Practical DNN Training and Loss Spikes Minimization Beyond Adam","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2211.12677","title":"Word-Level Representation From Bytes For Language Modeling","created":"2022-11-23","cited_by_count":0,"area":null},{"id":"2401.18046","title":"Multipath parsing in the brain","created":"2024-01-31","cited_by_count":0,"area":null},{"id":"2403.16125","title":"Arena: Efficiently Training Large Models via Dynamic Scheduling and Adaptive Parallelism Co-Design","created":"2024-03-24","cited_by_count":0,"area":null},{"id":"2405.13386","title":"360Zhinao Technical Report","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2509.18177","title":"A Framework for Generating Artificial Datasets to Validate Absolute and Relative Position Concepts","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2511.12131","title":"OAD-Promoter: Enhancing Zero-shot VQA using Large Language Models with Object Attribute Description","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2512.06734","title":"A Patient-Doctor-NLP-System to contest inequality for less privileged","created":"2025-12-07","cited_by_count":0,"area":null},{"id":"2512.24098","title":"Training a Huggingface Model on AWS Sagemaker (Without Tears)","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2603.28263","title":"Merge and Conquer: Instructing Multilingual Models by Adding Target Language Weights","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2605.17234","title":"Active Budget Allocation for Efficient Scaling Law Estimation via Surrogate-Guided Pruning","created":"2026-05-17","cited_by_count":0,"area":null}],"next_cursor":null}