{"total":84,"rows":[{"id":"2502.10341","title":"Organize the Web: Constructing Domains Enhances Pre-Training Data Curation","created":"2025-02-14","cited_by_count":76,"area":null},{"id":"2502.14127","title":"Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above","created":"2025-02-19","cited_by_count":52,"area":null},{"id":"2509.11106","title":"Fluid Language Model Benchmarking","created":"2025-09-14","cited_by_count":35,"area":null},{"id":"2407.07890","title":"Training on the Test Task Confounds Evaluation and Emergence","created":"2024-07-10","cited_by_count":34,"area":null},{"id":"2505.10833","title":"MergeBench: A Benchmark for Merging Domain-Specialized LLMs","created":"2025-05-16","cited_by_count":33,"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":"2507.06187","title":"The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains","created":"2025-07-08","cited_by_count":28,"area":null},{"id":"2508.13144","title":"Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation","created":"2025-08-18","cited_by_count":26,"area":null},{"id":"2508.01059","title":"Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report","created":"2025-08-01","cited_by_count":23,"area":null},{"id":"2501.01956","title":"Metadata Conditioning Accelerates Language Model Pre-training","created":"2025-01-03","cited_by_count":22,"area":null},{"id":"2503.01622","title":"DOVE: A Large-Scale Multi-Dimensional Predictions Dataset Towards Meaningful LLM Evaluation","created":"2025-03-03","cited_by_count":21,"area":null},{"id":"2511.18903","title":"How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining","created":"2025-11-24","cited_by_count":14,"area":null},{"id":"2412.17933","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","created":"2024-12-23","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":"2605.01640","title":"Prescriptive Scaling Laws for Data Constrained Training","created":"2026-05-02","cited_by_count":12,"area":null},{"id":"2410.23463","title":"MDCure: A Scalable Pipeline for Multi-Document Instruction-Following","created":"2024-10-30","cited_by_count":10,"area":null},{"id":"2512.15586","title":"Bolmo: Byteifying the Next Generation of Language Models","created":"2025-12-17","cited_by_count":9,"area":null},{"id":"2502.06244","title":"PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2503.15450","title":"SkyLadder: Better and Faster Pretraining via Context Window Scheduling","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2503.20110","title":"Efficient Model Development through Fine-tuning Transfer","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2509.23383","title":"Train Once, Answer All: Many Pretraining Experiments for the Cost of One","created":"2025-09-27","cited_by_count":6,"area":null},{"id":"2510.24626","title":"Relative Scaling Laws for LLMs","created":"2025-10-28","cited_by_count":6,"area":null},{"id":"2507.08472","title":"Pre-Training LLMs on a budget: A comparison of three optimizers","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2406.12822","title":"Is It Good Data for Multilingual Instruction Tuning or Just Bad Multilingual Evaluation for Large Language Models?","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2506.11389","title":"Curriculum-Guided Layer Scaling for Language Model Pretraining","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2507.08091","title":"Low-rank Momentum Factorization for Memory Efficient Training","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2605.18753","title":"DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention","created":"2026-05-18","cited_by_count":4,"area":null},{"id":"2508.03523","title":"FilBench: Can LLMs Understand and Generate Filipino?","created":"2025-08-05","cited_by_count":3,"area":null},{"id":"2510.20860","title":"Data-Centric Lessons To Improve Speech-Language Pretraining","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2602.04289","title":"Proxy Compression for Language Modeling","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2602.15210","title":"\\\"UberWeb: Insights from Multilingual Curation for a 20-Trillion-Token Dataset","created":"2026-02-16","cited_by_count":3,"area":null},{"id":"2604.15180","title":"AdaSplash-2: Faster Differentiable Sparse Attention","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2605.22769","title":"Understanding Data Temporality Impact on Large Language Models Pre-training","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2608.03624","title":"LoopMTP: A looped transformer guided by latent multi-token prediction","created":"2026-08-04","cited_by_count":3,"area":null},{"id":"2410.02744","title":"Neutral Residues: Revisiting Adapters for Model Extension","created":"2024-10-03","cited_by_count":2,"area":null},{"id":"2502.18798","title":"Choices Speak Louder than Questions","created":"2025-02-26","cited_by_count":2,"area":null},{"id":"2512.07612","title":"PCMind-2.1-Kaiyuan-2B Technical Report","created":"2025-12-08","cited_by_count":2,"area":null},{"id":"2601.19831","title":"Neural Neural Scaling Laws","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2605.30202","title":"A Dual-Path Architecture for Scaling Compute and Capacity in LLMs","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2609.02846","title":"UE5M3 FP4 Block Scaling for Stable Language Model Pretraining","created":"2026-09-02","cited_by_count":2,"area":null},{"id":"2411.15320","title":"PPLqa: An Unsupervised Information-Theoretic Quality Metric for Comparing Generative Large Language Models","created":"2024-11-22","cited_by_count":1,"area":null},{"id":"2505.12988","title":"Optimal Formats for Weight Quantisation","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2505.16570","title":"URLs Help, Topics Guide: Understanding Metadata Utility in LLM Training","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2601.03786","title":"Compact Example-Based Explanations for Language Models","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2604.12397","title":"KoCo: Conditioning Language Model Pre-training on Knowledge Coordinates","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2605.06105","title":"Shallow Prefill, Deep Decoding: Efficient Long-Context Inference via Layer-Asymmetric KV Visibility","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.26121","title":"GEM: Geometric Entropy Mixing for Optimal LLM Data Curation","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2608.10850","title":"Diffract: Spectral View of LLM Domain Adaptation","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2609.17380","title":"OPEN-1B: A Fully Auditable Training Run","created":"2026-09-15","cited_by_count":1,"area":null},{"id":"2502.19607","title":"Revisiting Word Embeddings in the LLM Era","created":"2025-02-26","cited_by_count":0,"area":null},{"id":"2506.03592","title":"From Understanding to Generation: An Efficient Shortcut for Evaluating Language Models","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2506.23527","title":"On Recipe Memorization and Creativity in Large Language Models: Is Your Model a Creative Cook, a Bad Cook, or Merely a Plagiator?","created":"2025-06-30","cited_by_count":0,"area":null},{"id":"2510.14261","title":"Rewriting History: A Recipe for Interventional Analyses to Study Data Effects on Model Behavior","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2512.13330","title":"FIN-bench-v2: A Unified and Robust Benchmark Suite for Evaluating Finnish Large Language Models","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2512.14549","title":"Dual-objective Language Models: Training Efficiency Without Overfitting","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2601.06463","title":"Gecko: An Efficient Neural Architecture Inherently Processing Sequences with Arbitrary Lengths","created":"2026-01-10","cited_by_count":0,"area":null},{"id":"2601.22699","title":"Models Know Models Best: Evaluation via Model-Preferred Formats","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.03846","title":"PLATE: Plasticity-Tunable Efficient Adapters for Geometry-Aware Continual Learning","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2603.03508","title":"Raising Bars, Not Parameters: LilMoo Compact Language Model for Hindi","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2603.13180","title":"MXNorm: Reusing MXFP block scales for efficient tensor normalisation","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.19294","title":"Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2604.00489","title":"Adapting Text LLMs to Speech via Multimodal Depth Up-Scaling","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2605.30916","title":"Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.06892","title":"GRASP: Geometry-aware Residual Alignment for Scalable Pretraining Data Attribution","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.15216","title":"Spokes: Optimizing for Diverse Pretraining Data Selection","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2607.02266","title":"HERMES: A Multi-Granularity Labeling Substrate for Pre-training Data Mixtures","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.10803","title":"Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.21279","title":"A Unified Moral-Value Dataset for Instruction Tuning","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.24585","title":"From Data to Device: ELMOD An Efficient German-First 2.7B Language Model for Mobile Inference","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.29887","title":"Check The Scoreboard: An Analysis of Scoring Schemes on Multiple-Choice Evaluation","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2608.30987","title":"Stick to What You Know: A Study of Knowledge-Aligned Supervised Fine-Tuning","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.15528","title":"To Each Language Its Tokenizer: Modular Tokenizers for Efficient Multilingual LLMs","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.23916","title":"Time-Incremental Continued Pretraining of LLMs: Knowledge Updates Without Catastrophic Forgetting","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.28395","title":"Fine-Tuning LLMs for Translation: General Forgetting Mitigation Does Not Preserve MT-Specific Instruction Following","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.32484","title":"Towards Scalable Data Diversification for Language Model Pretraining via Leverage Score Sampling","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.36860","title":"IronLLM: Forging Compact Edge-Native Language Models for Real-Time Embodied Intelligence","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38149","title":"Pretraining Latent Information Feedback Transformers with Teacher Supervision","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39114","title":"The Row Normalization Puzzle in Muon","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00053","title":"Format-Aware Fusion for Fast FP4 Pretraining","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2610.05978","title":"Byte Language Models: Scaling, Emergent Abstractions, and Information Allocation","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.15277","title":"Do correct answers have stable latent knowledge support?","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.16837","title":"A Scaled-Up Empirical Study of Syntactic Language Models","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.19185","title":"How to Evaluate When You Don't Know How to Evaluate? Choosing Reliable Setups for Base Language Model Benchmarking","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.20456","title":"The COUNT: Counting N-grams Unlocks Scaling on Host Memory and Training-Free Adaptation","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}