{"total":81,"rows":[{"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":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800,"area":null},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532,"area":null},{"id":"2310.06694","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","created":"2023-10-10","cited_by_count":415,"area":null},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403,"area":null},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189,"area":null},{"id":"2407.01492","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","created":"2024-07-01","cited_by_count":177,"area":null},{"id":"2402.14848","title":"Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models","created":"2024-02-19","cited_by_count":152,"area":"lr"},{"id":"2404.07965","title":"Rho-1: Not All Tokens Are What You Need","created":"2024-04-11","cited_by_count":133,"area":null},{"id":"2405.10938","title":"Observational Scaling Laws and the Predictability of Language Model Performance","created":"2024-05-17","cited_by_count":130,"area":null},{"id":"2309.07311","title":"Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs","created":"2023-09-13","cited_by_count":124,"area":null},{"id":"2306.00622","title":"ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper Reviewing","created":"2023-06-01","cited_by_count":122,"area":null},{"id":"2307.15936","title":"A Theory for Emergence of Complex Skills in Language Models","created":"2023-07-29","cited_by_count":113,"area":null},{"id":"2310.19341","title":"Skywork: A More Open Bilingual Foundation Model","created":"2023-10-30","cited_by_count":112,"area":null},{"id":"2403.15796","title":"Understanding Emergent Abilities of Language Models from the Loss Perspective","created":"2024-03-23","cited_by_count":94,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2406.11813","title":"How Do Large Language Models Acquire Factual Knowledge During Pretraining?","created":"2024-06-17","cited_by_count":90,"area":null},{"id":"2311.13240","title":"On the Calibration of Large Language Models and Alignment","created":"2023-11-22","cited_by_count":73,"area":null},{"id":"2407.10827","title":"LLM Circuit Analyses Are Consistent Across Training and Scale","created":"2024-07-15","cited_by_count":63,"area":null},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"area":null},{"id":"2404.09937","title":"Compression Represents Intelligence Linearly","created":"2024-04-15","cited_by_count":56,"area":null},{"id":"2402.12847","title":"Instruction-tuned Language Models are Better Knowledge Learners","created":"2024-02-20","cited_by_count":55,"area":null},{"id":"2312.10523","title":"Paloma: A Benchmark for Evaluating Language Model Fit","created":"2023-12-16","cited_by_count":54,"area":null},{"id":"2501.17047","title":"How Linguistics Learned to Stop Worrying and Love the Language Models","created":"2025-01-28","cited_by_count":51,"area":null},{"id":"2402.16775","title":"A Comprehensive Evaluation of Quantization Strategies for Large Language Models","created":"2024-02-26","cited_by_count":48,"area":null},{"id":"2501.16265","title":"Training Dynamics of In-Context Learning in Linear Attention","created":"2025-01-27","cited_by_count":46,"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":"2402.02255","title":"Frequency Explains the Inverse Correlation of Large Language Models' Size, Training Data Amount, and Surprisal's Fit to Reading Times","created":"2024-02-03","cited_by_count":39,"area":null},{"id":"2406.13229","title":"Probing the Emergence of Cross-lingual Alignment during LLM Training","created":"2024-06-19","cited_by_count":39,"area":null},{"id":"2306.03241","title":"Early Weight Averaging meets High Learning Rates for LLM Pre-training","created":"2023-06-05","cited_by_count":37,"area":null},{"id":"2308.15419","title":"Characterizing Learning Curves During Language Model Pre-Training: Learning, Forgetting, and Stability","created":"2023-08-29","cited_by_count":35,"area":null},{"id":"2411.05735","title":"Aioli: A Unified Optimization Framework for Language Model Data Mixing","created":"2024-11-08","cited_by_count":34,"area":null},{"id":"2311.09205","title":"When Is Multilinguality a Curse? Language Modeling for 250 High- and Low-Resource Languages","created":"2023-11-15","cited_by_count":32,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2408.10441","title":"Goldfish: Monolingual Language Models for 350 Languages","created":"2024-08-19","cited_by_count":29,"area":null},{"id":"2507.00885","title":"Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check","created":"2025-07-01","cited_by_count":29,"area":null},{"id":"2410.11840","title":"A Hitchhiker's Guide to Scaling Law Estimation","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2401.00788","title":"Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models","created":"2024-01-01","cited_by_count":23,"area":null},{"id":"2307.03749","title":"On the Efficacy of Sampling Adapters","created":"2023-07-07","cited_by_count":17,"area":null},{"id":"2405.13828","title":"Babysit A Language Model From Scratch: Interactive Language Learning by Trials and Demonstrations","created":"2024-05-22","cited_by_count":12,"area":null},{"id":"2507.05195","title":"Train-before-Test Harmonizes Language Model Rankings","created":"2025-07-07","cited_by_count":12,"area":null},{"id":"2306.11475","title":"Delegated Classification","created":"2023-06-20","cited_by_count":10,"area":null},{"id":"2411.16035","title":"Predicting Emergent Capabilities by Finetuning","created":"2024-11-25","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":"2407.02596","title":"Towards More Realistic Extraction Attacks: An Adversarial Perspective","created":"2024-07-02","cited_by_count":8,"area":null},{"id":"2505.18513","title":"Enhancing Training Data Attribution with Representational Optimization","created":"2025-05-24","cited_by_count":8,"area":null},{"id":"2402.12170","title":"Where is the answer? Investigating Positional Bias in Language Model Knowledge Extraction","created":"2024-02-16","cited_by_count":6,"area":null},{"id":"2504.02273","title":"Reasoning Under 1 Billion: Memory-Augmented Reinforcement Learning for Large Language Models","created":"2025-04-03","cited_by_count":6,"area":"lr"},{"id":"2510.13796","title":"The Mechanistic Emergence of Symbol Grounding in Language Models","created":"2025-10-15","cited_by_count":6,"area":null},{"id":"2506.00288","title":"Emergent Abilities of Large Language Models under Continued Pretraining for Language Adaptation","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2506.02204","title":"BehaviorBox: Automated Discovery of Fine-Grained Performance Differences Between Language Models","created":"2025-06-02","cited_by_count":5,"area":null},{"id":"2509.16332","title":"Psychometric Personality Shaping Modulates Capabilities and Safety in Language Models","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2510.04848","title":"Instability in Downstream Task Performance During LLM Pretraining","created":"2025-10-06","cited_by_count":4,"area":null},{"id":"2402.03822","title":"RevOrder: A Novel Method for Enhanced Arithmetic in Language Models","created":"2024-02-06","cited_by_count":3,"area":null},{"id":"2409.00592","title":"Hyper-Compression: Model Compression via Hyperfunction","created":"2024-09-01","cited_by_count":3,"area":null},{"id":"2502.10140","title":"Small Models, Big Impact: Efficient Corpus and Graph-Based Adaptation of Small Multilingual Language Models for Low-Resource Languages","created":"2025-02-14","cited_by_count":3,"area":null},{"id":"2409.06131","title":"Accelerating Large Language Model Pretraining via LFR Pedagogy: Learn, Focus, and Review","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2412.07111","title":"Predictable Emergent Abilities of LLMs: Proxy Tasks Are All You Need","created":"2024-12-10","cited_by_count":2,"area":null},{"id":"2603.13381","title":"Beyond Linearity in Attention Projections: The Case for Nonlinear Queries","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2608.11859","title":"Small-Scale Experiments: Are We There Yet?","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2501.02068","title":"The interplay between domain specialization and model size","created":"2025-01-03","cited_by_count":1,"area":null},{"id":"2506.01709","title":"Fairness Dynamics During Training","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2506.13216","title":"Capability Salience Vector: Fine-grained Alignment of Loss and Capabilities for Downstream Task Scaling Law","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2601.10986","title":"ZPD Detector: Data Selection via Capability-Difficulty Alignment for Large Language Models","created":"2026-01-16","cited_by_count":1,"area":"alignment"},{"id":"2606.29858","title":"Smooth Scaling Laws Hide Stepwise Token Learning","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2505.14523","title":"Exploring Graph Representations of Logical Forms for Language Modeling","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2506.03434","title":"Time Course MechInterp: Analyzing the Evolution of Components and Knowledge in Large Language Models","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2512.09394","title":"Language models as tools for investigating the distinction between possible and impossible natural languages","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2512.12447","title":"Large language models have learned to use language","created":"2025-12-13","cited_by_count":0,"area":null},{"id":"2512.13441","title":"Large language models are not about natural language","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2512.14506","title":"Linguists should learn to love speech-based deep learning models","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2601.10421","title":"Are Language Models Models?","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2602.14301","title":"DeepFusion: Accelerating MoE Training via Federated Knowledge Distillation from Heterogeneous Edge Devices","created":"2026-02-15","cited_by_count":0,"area":"moe"},{"id":"2603.15953","title":"A Family of LLMs Liberated from Static Vocabularies","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2604.09466","title":"Across the Levels of Analysis: Explaining Predictive Processing in Humans Requires More Than Machine-Estimated Probabilities","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.09501","title":"You Can't Fight in Here! This is BBS!","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.10061","title":"Not-So-Strange Love: Language Models and Generative Linguistic Theories are More Compatible than They Appear","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2607.16549","title":"Encoding EEG Signals to Examine Human-Like Next-Word Prediction Behaviour in Language Models","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2609.08618","title":"Target-Independent Micro-Interventions for Predicting Training Response Across Language-Model Families","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.15522","title":"Psychosis involves a deficit of information compression in connected speech","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2610.02491","title":"What Does a Token Cost? A Mixture-of-Agents Measurement of Sufficient Per-Token Compute","created":"2026-10-01","cited_by_count":0,"area":"agents"}],"next_cursor":null}