{"total":80,"rows":[{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512,"area":null},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019,"area":null},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512,"area":null},{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906,"area":null},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843,"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":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713,"area":null},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535,"area":null},{"id":"2204.05999","title":"InCoder: A Generative Model for Code Infilling and Synthesis","created":"2022-04-12","cited_by_count":498,"area":null},{"id":"2207.04429","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","created":"2022-07-10","cited_by_count":439,"area":null},{"id":"2202.01169","title":"Unified Scaling Laws for Routed Language Models","created":"2022-02-02","cited_by_count":253,"area":null},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236,"area":null},{"id":"2205.10770","title":"Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models","created":"2022-05-22","cited_by_count":220,"area":null},{"id":"2208.03306","title":"Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models","created":"2022-08-05","cited_by_count":191,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2308.12284","title":"D4: Improving LLM Pretraining via Document De-Duplication and Diversification","created":"2023-08-23","cited_by_count":150,"area":null},{"id":"2201.07520","title":"CM3: A Causal Masked Multimodal Model of the Internet","created":"2022-01-19","cited_by_count":142,"area":null},{"id":"2304.11633","title":"Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness","created":"2023-04-23","cited_by_count":130,"area":null},{"id":"2310.10378","title":"Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models","created":"2023-10-16","cited_by_count":118,"area":null},{"id":"2204.10628","title":"Autoregressive Search Engines: Generating Substrings as Document Identifiers","created":"2022-04-22","cited_by_count":113,"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":"2409.15790","title":"Small Language Models: Survey, Measurements, and Insights","created":"2024-09-24","cited_by_count":112,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2403.02181","title":"Not All Layers of LLMs Are Necessary During Inference","created":"2024-03-04","cited_by_count":96,"area":null},{"id":"2212.09535","title":"BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting","created":"2022-12-19","cited_by_count":90,"area":null},{"id":"2302.07027","title":"AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models","created":"2023-02-14","cited_by_count":84,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2212.06713","title":"Structured Prompting: Scaling In-Context Learning to 1,000 Examples","created":"2022-12-13","cited_by_count":81,"area":null},{"id":"2212.09803","title":"Training Trajectories of Language Models Across Scales","created":"2022-12-19","cited_by_count":81,"area":null},{"id":"2310.14735","title":"Unleashing the potential of prompt engineering for large language models","created":"2023-10-23","cited_by_count":72,"area":null},{"id":"2402.03804","title":"ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs","created":"2024-02-06","cited_by_count":67,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2303.14177","title":"Scaling Expert Language Models with Unsupervised Domain Discovery","created":"2023-03-24","cited_by_count":60,"area":null},{"id":"2205.01703","title":"Improving In-Context Few-Shot Learning via Self-Supervised Training","created":"2022-05-03","cited_by_count":57,"area":null},{"id":"2303.10845","title":"PanGu-{\\Sigma}: Towards Trillion Parameter Language Model with Sparse Heterogeneous Computing","created":"2023-03-20","cited_by_count":56,"area":null},{"id":"2305.19268","title":"Intriguing Properties of Quantization at Scale","created":"2023-05-30","cited_by_count":49,"area":null},{"id":"2309.08520","title":"Scaling Laws for Sparsely-Connected Foundation Models","created":"2023-09-15","cited_by_count":43,"area":null},{"id":"2410.07064","title":"Data Selection via Optimal Control for Language Models","created":"2024-10-09","cited_by_count":38,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2401.17671","title":"Contextual Feature Extraction Hierarchies Converge in Large Language Models and the Brain","created":"2024-01-31","cited_by_count":32,"area":null},{"id":"2312.06786","title":"Mixture-of-Linear-Experts for Long-term Time Series Forecasting","created":"2023-12-11","cited_by_count":29,"area":null},{"id":"2202.07101","title":"A Survey on Dynamic Neural Networks for Natural Language Processing","created":"2022-02-15","cited_by_count":24,"area":null},{"id":"2204.06644","title":"METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals","created":"2022-04-13","cited_by_count":20,"area":null},{"id":"2311.15436","title":"Learning to Skip for Language Modeling","created":"2023-11-26","cited_by_count":19,"area":null},{"id":"2210.12574","title":"The Curious Case of Absolute Position Embeddings","created":"2022-10-23","cited_by_count":17,"area":null},{"id":"2205.11726","title":"On the Role of Bidirectionality in Language Model Pre-Training","created":"2022-05-24","cited_by_count":15,"area":null},{"id":"2310.02784","title":"MAD Max Beyond Single-Node: Enabling Large Machine Learning Model Acceleration on Distributed Systems","created":"2023-10-04","cited_by_count":14,"area":null},{"id":"2312.06798","title":"Building Trustworthy NeuroSymbolic AI Systems: Consistency, Reliability, Explainability, and Safety","created":"2023-12-05","cited_by_count":14,"area":null},{"id":"2212.03597","title":"DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing","created":"2022-12-07","cited_by_count":13,"area":null},{"id":"2308.05502","title":"Bringing order into the realm of Transformer-based language models for artificial intelligence and law","created":"2023-08-10","cited_by_count":13,"area":null},{"id":"2510.27172","title":"Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler","created":"2025-10-31","cited_by_count":12,"area":null},{"id":"2211.08099","title":"A Universal Discriminator for Zero-Shot Generalization","created":"2022-11-15","cited_by_count":11,"area":null},{"id":"2403.05636","title":"Tuning-Free Accountable Intervention for LLM Deployment -- A Metacognitive Approach","created":"2024-03-08","cited_by_count":11,"area":null},{"id":"2403.10616","title":"DiPaCo: Distributed Path Composition","created":"2024-03-15","cited_by_count":10,"area":null},{"id":"2310.08309","title":"Not All Demonstration Examples are Equally Beneficial: Reweighting Demonstration Examples for In-Context Learning","created":"2023-10-12","cited_by_count":9,"area":null},{"id":"2412.15178","title":"HPC-Coder-V2: Studying Code LLMs Across Low-Resource Parallel Languages","created":"2024-12-19","cited_by_count":8,"area":null},{"id":"2506.21545","title":"Data Efficacy for Language Model Training","created":"2025-06-26","cited_by_count":8,"area":null},{"id":"2409.01990","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","created":"2024-09-03","cited_by_count":7,"area":null},{"id":"2212.09686","title":"A Natural Bias for Language Generation Models","created":"2022-12-19","cited_by_count":6,"area":null},{"id":"2403.07322","title":"A Question-centric Multi-experts Contrastive Learning Framework for Improving the Accuracy and Interpretability of Deep Sequential Knowledge Tracing Models","created":"2024-03-12","cited_by_count":5,"area":null},{"id":"2410.03529","title":"No Need to Talk: Asynchronous Mixture of Language Models","created":"2024-10-04","cited_by_count":5,"area":null},{"id":"2501.08413","title":"Labeling Free-text Data using Language Model Ensembles","created":"2025-01-14","cited_by_count":5,"area":null},{"id":"2505.22107","title":"Curse of High Dimensionality Issue in Transformer for Long-context Modeling","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2302.05454","title":"Distillation of encoder-decoder transformers for sequence labelling","created":"2023-02-10","cited_by_count":3,"area":null},{"id":"2401.07994","title":"Assessing the Latent Automated Program Repair Capabilities of Large Language Models using Round-Trip Translation","created":"2024-01-15","cited_by_count":3,"area":null},{"id":"2409.15764","title":"Spatial-Temporal Mixture-of-Graph-Experts for Multi-Type Crime Prediction","created":"2024-09-24","cited_by_count":3,"area":null},{"id":"2205.15223","title":"Prompting ELECTRA: Few-Shot Learning with Discriminative Pre-Trained Models","created":"2022-05-30","cited_by_count":2,"area":null},{"id":"2207.10617","title":"Leveraging Natural Supervision for Language Representation Learning and Generation","created":"2022-07-21","cited_by_count":2,"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":"2311.07611","title":"Intentional Biases in LLM Responses","created":"2023-11-11","cited_by_count":2,"area":null},{"id":"2602.02886","title":"Mixture of Concept Bottleneck Experts","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2302.02721","title":"Multipath agents for modular multitask ML systems","created":"2023-02-06","cited_by_count":1,"area":null},{"id":"2402.18434","title":"Graph Regularized Encoder Training for Extreme Classification","created":"2024-02-28","cited_by_count":1,"area":null},{"id":"2404.12897","title":"Enabling Natural Zero-Shot Prompting on Encoder Models via Statement-Tuning","created":"2024-04-19","cited_by_count":1,"area":null},{"id":"2406.13351","title":"A Resource-Adaptive Approach for Federated Learning under Resource-Constrained Environments","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2503.10881","title":"SCE: Scalable Consistency Ensembles Make Blackbox Large Language Model Generation More Reliable","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2504.18929","title":"Revisiting Transformers through the Lens of Low Entropy and Dynamic Sparsity","created":"2025-04-26","cited_by_count":1,"area":null},{"id":"2506.01592","title":"Statement-Tuning Enables Efficient Cross-lingual Generalization in Encoder-only Models","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2312.15388","title":"DEAP: Design Space Exploration for DNN Accelerator Parallelism","created":"2023-12-24","cited_by_count":0,"area":null},{"id":"2602.10585","title":"Neural Additive Experts: Context-Gated Experts for Controllable Model Additivity","created":"2026-02-11","cited_by_count":0,"area":null}],"next_cursor":null}