{"total":308,"rows":[{"id":"2306.11644","title":"Textbooks Are All You Need","created":"2023-06-20","cited_by_count":569,"area":null},{"id":"2309.05463","title":"Textbooks Are All You Need II: phi-1.5 technical report","created":"2023-09-11","cited_by_count":565,"area":null},{"id":"2309.12288","title":"The Reversal Curse: LLMs trained on \"A is B\" fail to learn \"B is A\"","created":"2023-09-21","cited_by_count":407,"area":null},{"id":"2309.14316","title":"Physics of Language Models: Part 3.1, Knowledge Storage and Extraction","created":"2023-09-25","cited_by_count":270,"area":null},{"id":"2401.16380","title":"Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling","created":"2024-01-29","cited_by_count":161,"area":null},{"id":"2412.02595","title":"Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset","created":"2024-12-03","cited_by_count":160,"area":null},{"id":"2309.00667","title":"Taken out of context: On measuring situational awareness in LLMs","created":"2023-09-01","cited_by_count":143,"area":null},{"id":"2401.03601","title":"InFoBench: Evaluating Instruction Following Ability in Large Language Models","created":"2024-01-07","cited_by_count":135,"area":null},{"id":"2311.12786","title":"Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks","created":"2023-11-21","cited_by_count":115,"area":null},{"id":"2409.15790","title":"Small Language Models: Survey, Measurements, and Insights","created":"2024-09-24","cited_by_count":112,"area":null},{"id":"2506.10943","title":"Self-Adapting Language Models","created":"2025-06-12","cited_by_count":84,"area":null},{"id":"2306.00946","title":"Exposing Attention Glitches with Flip-Flop Language Modeling","created":"2023-06-01","cited_by_count":75,"area":null},{"id":"2308.01399","title":"Learning to Model the World with Language","created":"2023-07-31","cited_by_count":68,"area":null},{"id":"2405.14813","title":"Scalable Optimization in the Modular Norm","created":"2024-05-23","cited_by_count":68,"area":null},{"id":"2403.19827","title":"Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNs","created":"2024-03-28","cited_by_count":65,"area":null},{"id":"2308.09067","title":"Contrasting Linguistic Patterns in Human and LLM-Generated News Text","created":"2023-08-17","cited_by_count":62,"area":null},{"id":"2410.16713","title":"Collapse or Thrive? Perils and Promises of Synthetic Data in a Self-Generating World","created":"2024-10-22","cited_by_count":52,"area":null},{"id":"2412.05149","title":"Findings of the Second BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora","created":"2024-12-06","cited_by_count":48,"area":null},{"id":"2403.07384","title":"SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models","created":"2024-03-12","cited_by_count":44,"area":null},{"id":"2402.02364","title":"Loss Landscape Degeneracy and Stagewise Development in Transformers","created":"2024-02-04","cited_by_count":40,"area":null},{"id":"2410.02984","title":"Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient","created":"2024-10-03","cited_by_count":40,"area":null},{"id":"2405.17767","title":"Linguistic Collapse: Neural Collapse in (Large) Language Models","created":"2024-05-28","cited_by_count":38,"area":null},{"id":"2403.12844","title":"MELTing point: Mobile Evaluation of Language Transformers","created":"2024-03-19","cited_by_count":36,"area":null},{"id":"2407.18333","title":"AutoVCoder: A Systematic Framework for Automated Verilog Code Generation using LLMs","created":"2024-07-21","cited_by_count":36,"area":null},{"id":"2510.15511","title":"Language Models are Injective and Hence Invertible","created":"2025-10-17","cited_by_count":35,"area":null},{"id":"2410.04332","title":"Gradient Routing: Masking Gradients to Localize Computation in Neural Networks","created":"2024-10-06","cited_by_count":34,"area":null},{"id":"2309.08632","title":"Pretraining on the Test Set Is All You Need","created":"2023-09-13","cited_by_count":33,"area":null},{"id":"2401.03315","title":"Malla: Demystifying Real-world Large Language Model Integrated Malicious Services","created":"2024-01-06","cited_by_count":33,"area":null},{"id":"2404.00685","title":"Scaling Properties of Speech Language Models","created":"2024-03-31","cited_by_count":32,"area":null},{"id":"2404.18001","title":"LLMParser: An Exploratory Study on Using Large Language Models for Log Parsing","created":"2024-04-27","cited_by_count":32,"area":null},{"id":"2310.06827","title":"Teaching Language Models to Hallucinate Less with Synthetic Tasks","created":"2023-10-10","cited_by_count":31,"area":null},{"id":"2409.15452","title":"CUTE: Measuring LLMs' Understanding of Their Tokens","created":"2024-09-23","cited_by_count":31,"area":null},{"id":"2506.04689","title":"Recycling the Web: A Method to Enhance Pre-training Data Quality and Quantity for Language Models","created":"2025-06-05","cited_by_count":31,"area":null},{"id":"2408.15545","title":"SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding","created":"2024-08-28","cited_by_count":29,"area":null},{"id":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26,"area":null},{"id":"2407.12034","title":"Understanding Transformers via N-gram Statistics","created":"2024-06-30","cited_by_count":26,"area":null},{"id":"2312.02073","title":"A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia","created":"2023-12-04","cited_by_count":24,"area":null},{"id":"2408.03617","title":"Is Child-Directed Speech Effective Training Data for Language Models?","created":"2024-08-07","cited_by_count":24,"area":null},{"id":"2408.07144","title":"Language Models as Models of Language","created":"2024-08-13","cited_by_count":24,"area":null},{"id":"2408.15417","title":"Implicit Geometry of Next-token Prediction: From Language Sparsity Patterns to Model Representations","created":"2024-08-27","cited_by_count":24,"area":null},{"id":"2405.12250","title":"Your Transformer is Secretly Linear","created":"2024-05-19","cited_by_count":23,"area":null},{"id":"2602.07488","title":"Deriving Neural Scaling Laws from the statistics of natural language","created":"2026-02-07","cited_by_count":23,"area":null},{"id":"2402.04084","title":"Provably learning a multi-head attention layer","created":"2024-02-06","cited_by_count":21,"area":null},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2510.22980","title":"How Muon's Spectral Design Benefits Generalization: A Study on Imbalanced Data","created":"2025-10-27","cited_by_count":19,"area":null},{"id":"2404.11122","title":"Small Language Models are Good Too: An Empirical Study of Zero-Shot Classification","created":"2024-04-17","cited_by_count":18,"area":null},{"id":"2402.16828","title":"Training Neural Networks from Scratch with Parallel Low-Rank Adapters","created":"2024-02-26","cited_by_count":17,"area":null},{"id":"2404.04360","title":"Prompt Public Large Language Models to Synthesize Data for Private On-device Applications","created":"2024-04-05","cited_by_count":17,"area":null},{"id":"2409.11547","title":"Small Language Models can Outperform Humans in Short Creative Writing: A Study Comparing SLMs with Humans and LLMs","created":"2024-09-17","cited_by_count":17,"area":null},{"id":"2410.04368","title":"Algorithmic Capabilities of Random Transformers","created":"2024-10-06","cited_by_count":17,"area":null},{"id":"2502.13252","title":"Multilingual Language Model Pretraining using Machine-translated Data","created":"2025-02-18","cited_by_count":17,"area":null},{"id":"2505.24333","title":"Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation","created":"2025-05-30","cited_by_count":17,"area":null},{"id":"2510.13632","title":"Closing the Gap Between Text and Speech Understanding in LLMs","created":"2025-10-15","cited_by_count":17,"area":null},{"id":"2405.06394","title":"Memory Mosaics","created":"2024-05-10","cited_by_count":16,"area":null},{"id":"2310.17428","title":"''Fifty Shades of Bias'': Normative Ratings of Gender Bias in GPT Generated English Text","created":"2023-10-26","cited_by_count":15,"area":null},{"id":"2406.03030","title":"From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation","created":"2024-06-05","cited_by_count":15,"area":null},{"id":"2310.11428","title":"Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression","created":"2023-10-17","cited_by_count":14,"area":null},{"id":"2602.11164","title":"Automated Optimization Modeling via a Localizable Error-Driven Perspective","created":"2026-01-17","cited_by_count":14,"area":null},{"id":"2307.10274","title":"Zero-shot Domain-sensitive Speech Recognition with Prompt-conditioning Fine-tuning","created":"2023-07-18","cited_by_count":13,"area":null},{"id":"2406.05690","title":"MoPS: Modular Story Premise Synthesis for Open-Ended Automatic Story Generation","created":"2024-06-09","cited_by_count":13,"area":null},{"id":"2411.02572","title":"ViTally Consistent: Scaling Biological Representation Learning for Cell Microscopy","created":"2024-11-04","cited_by_count":13,"area":null},{"id":"2407.19580","title":"Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures","created":"2024-07-28","cited_by_count":12,"area":null},{"id":"2410.23506","title":"The Belief State Transformer","created":"2024-10-30","cited_by_count":12,"area":null},{"id":"2502.15007","title":"LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers","created":"2025-02-20","cited_by_count":12,"area":null},{"id":"2502.15814","title":"Slamming: Training a Speech Language Model on One GPU in a Day","created":"2025-02-19","cited_by_count":12,"area":null},{"id":"2405.13718","title":"Next-token prediction capacity: general upper bounds and a lower bound for transformers","created":"2024-05-22","cited_by_count":11,"area":null},{"id":"2408.04413","title":"Deeploy: Enabling Energy-Efficient Deployment of Small Language Models On Heterogeneous Microcontrollers","created":"2024-08-08","cited_by_count":11,"area":null},{"id":"2410.18808","title":"Delving into the Reversal Curse: How Far Can Large Language Models Generalize?","created":"2024-10-24","cited_by_count":11,"area":null},{"id":"2412.15184","title":"Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning","created":"2024-12-19","cited_by_count":11,"area":null},{"id":"2505.05755","title":"Insertion Language Models: Sequence Generation with Arbitrary-Position Insertions","created":"2025-05-09","cited_by_count":11,"area":null},{"id":"2606.24773","title":"Posterior Refinement: Fast Language Generation via Any-Order Flow Maps","created":"2026-06-23","cited_by_count":11,"area":null},{"id":"2309.16573","title":"Language Models as a Service: Overview of a New Paradigm and its Challenges","created":"2023-09-28","cited_by_count":10,"area":null},{"id":"2402.19282","title":"WanJuan-CC: A Safe and High-Quality Open-sourced English Webtext Dataset","created":"2024-02-29","cited_by_count":10,"area":null},{"id":"2504.09184","title":"Parameterized Synthetic Text Generation with SimpleStories","created":"2025-04-12","cited_by_count":10,"area":null},{"id":"2509.26404","title":"SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From","created":"2025-09-30","cited_by_count":10,"area":null},{"id":"2405.15926","title":"Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers","created":"2024-05-24","cited_by_count":9,"area":null},{"id":"2502.10927","title":"The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training","created":"2025-02-15","cited_by_count":9,"area":null},{"id":"2503.21023","title":"Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework","created":"2025-03-26","cited_by_count":9,"area":null},{"id":"2510.25771","title":"Gaperon: A Peppered English-French Generative Language Model Suite","created":"2025-10-29","cited_by_count":9,"area":null},{"id":"2406.16767","title":"The GPT-WritingPrompts Dataset: A Comparative Analysis of Character Portrayal in Short Stories","created":"2024-06-24","cited_by_count":8,"area":null},{"id":"2410.17765","title":"Faster Language Models with Better Multi-Token Prediction Using Tensor Decomposition","created":"2024-10-23","cited_by_count":8,"area":null},{"id":"2507.08892","title":"Multi-Actor Generative Artificial Intelligence as a Game Engine","created":"2025-07-10","cited_by_count":8,"area":null},{"id":"2602.06791","title":"Rare Event Analysis of Large Language Models","created":"2026-02-06","cited_by_count":8,"area":null},{"id":"2311.01955","title":"Too Much Information: Keeping Training Simple for BabyLMs","created":"2023-11-03","cited_by_count":7,"area":null},{"id":"2402.17759","title":"Towards Optimal Learning of Language Models","created":"2024-02-27","cited_by_count":7,"area":null},{"id":"2404.02204","title":"Emergent Abilities in Reduced-Scale Generative Language Models","created":"2024-04-02","cited_by_count":7,"area":null},{"id":"2405.14159","title":"Super Tiny Language Models","created":"2024-05-23","cited_by_count":7,"area":null},{"id":"2407.00416","title":"Too Late to Train, Too Early To Use? A Study on Necessity and Viability of Low-Resource Bengali LLMs","created":"2024-06-29","cited_by_count":7,"area":null},{"id":"2505.19103","title":"WHISTRESS: Enriching Transcriptions with Sentence Stress Detection","created":"2025-05-25","cited_by_count":7,"area":null},{"id":"2507.09937","title":"Memorization Sinks: Isolating Memorization during LLM Training","created":"2025-07-14","cited_by_count":7,"area":null},{"id":"2510.00379","title":"Composer: A Search Framework for Hybrid Neural Architecture Design","created":"2025-10-01","cited_by_count":7,"area":null},{"id":"2603.03646","title":"InfinityStory: Unlimited Video Generation with World Consistency and Character-Aware Shot Transitions","created":"2026-03-04","cited_by_count":7,"area":null},{"id":"2603.18534","title":"Data-efficient pre-training by scaling synthetic megadocs","created":"2026-03-19","cited_by_count":7,"area":null},{"id":"2310.10692","title":"ACES: Generating Diverse Programming Puzzles with with Autotelic Generative Models","created":"2023-10-15","cited_by_count":6,"area":null},{"id":"2403.13638","title":"Pretraining Language Models Using Translationese","created":"2024-03-20","cited_by_count":6,"area":null},{"id":"2408.03506","title":"1.5-Pints Technical Report: Pretraining in Days, Not Months -- Your Language Model Thrives on Quality Data","created":"2024-08-07","cited_by_count":6,"area":null},{"id":"2409.15298","title":"Sorbet: A Neuromorphic Hardware-Compatible Transformer-Based Spiking Language Model","created":"2024-09-04","cited_by_count":6,"area":null},{"id":"2410.05639","title":"DecorateLM: Data Engineering through Corpus Rating, Tagging, and Editing with Language Models","created":"2024-10-08","cited_by_count":6,"area":null},{"id":"2411.12986","title":"Training Bilingual LMs with Data Constraints in the Targeted Language","created":"2024-11-20","cited_by_count":6,"area":null},{"id":"2502.16570","title":"Entropy-Lens: Uncovering Decision Strategies in LLMs","created":"2025-02-23","cited_by_count":6,"area":null}],"next_cursor":"100"}