{"total":236,"rows":[{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494,"area":null},{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"area":"moe"},{"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":"2404.05892","title":"Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence","created":"2024-04-08","cited_by_count":159,"area":null},{"id":"2506.01937","title":"RewardBench 2: Advancing Reward Model Evaluation","created":"2025-06-02","cited_by_count":150,"area":"alignment"},{"id":"2410.12832","title":"Generative Reward Models","created":"2024-10-02","cited_by_count":148,"area":"alignment"},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"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":"2501.04682","title":"Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought","created":"2025-01-08","cited_by_count":109,"area":"lr"},{"id":"2502.17387","title":"Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models","created":"2025-02-24","cited_by_count":109,"area":"lr"},{"id":"2406.06046","title":"MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models","created":"2024-06-10","cited_by_count":100,"area":null},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75,"area":"mllm"},{"id":"2406.06391","title":"Towards Lifelong Learning of Large Language Models: A Survey","created":"2024-06-10","cited_by_count":64,"area":null},{"id":"2406.14491","title":"Instruction Pre-Training: Language Models are Supervised Multitask Learners","created":"2024-06-20","cited_by_count":63,"area":null},{"id":"2506.05316","title":"Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay","created":"2025-06-05","cited_by_count":56,"area":"lr"},{"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":"2410.11820","title":"Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws","created":"2024-10-15","cited_by_count":47,"area":null},{"id":"2506.18896","title":"ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs","created":"2025-06-23","cited_by_count":46,"area":"lr"},{"id":"2406.07515","title":"Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification","created":"2024-06-11","cited_by_count":45,"area":"synth"},{"id":"2407.06645","title":"Entropy Law: The Story Behind Data Compression and LLM Performance","created":"2024-07-09","cited_by_count":44,"area":null},{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"area":null},{"id":"2407.19584","title":"SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain","created":"2024-07-28","cited_by_count":39,"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":"2405.16122","title":"Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars","created":"2024-05-25","cited_by_count":37,"area":null},{"id":"2502.09650","title":"Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples","created":"2025-02-11","cited_by_count":37,"area":"alignment"},{"id":"2508.21148","title":"A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers","created":"2025-08-28","cited_by_count":37,"area":"agents"},{"id":"2412.02980","title":"Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models","created":"2024-12-04","cited_by_count":35,"area":"synth"},{"id":"2407.07890","title":"Training on the Test Task Confounds Evaluation and Emergence","created":"2024-07-10","cited_by_count":34,"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":"2410.17637","title":"MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models","created":"2024-10-23","cited_by_count":34,"area":"mllm"},{"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":"2502.02871","title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","created":"2025-02-05","cited_by_count":33,"area":"lr"},{"id":"2405.20535","title":"Unveiling the Impact of Coding Data Instruction Fine-Tuning on Large Language Models Reasoning","created":"2024-05-30","cited_by_count":31,"area":"lr"},{"id":"2408.02085","title":"Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models","created":"2024-08-04","cited_by_count":29,"area":"alignment"},{"id":"2410.19133","title":"Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback","created":"2024-10-24","cited_by_count":26,"area":"alignment"},{"id":"2412.14689","title":"How to Synthesize Text Data without Model Collapse?","created":"2024-12-19","cited_by_count":25,"area":"synth"},{"id":"2411.15102","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","created":"2024-11-22","cited_by_count":23,"area":null},{"id":"2501.12147","title":"Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities","created":"2025-01-21","cited_by_count":23,"area":null},{"id":"2506.19121","title":"CUPID: Curating Data your Robot Loves with Influence Functions","created":"2025-06-23","cited_by_count":23,"area":"offlinerl"},{"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":"2508.10858","title":"Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation","created":"2025-08-14","cited_by_count":21,"area":"alignment"},{"id":"2405.09373","title":"PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models","created":"2024-05-15","cited_by_count":20,"area":null},{"id":"2411.10914","title":"BPO: Towards Balanced Preference Optimization between Knowledge Breadth and Depth in Alignment","created":"2024-11-16","cited_by_count":20,"area":"alignment"},{"id":"2406.05184","title":"The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better","created":"2024-06-07","cited_by_count":19,"area":null},{"id":"2504.14194","title":"Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models","created":"2025-04-19","cited_by_count":19,"area":null},{"id":"2507.12466","title":"Language Models Improve When Pretraining Data Matches Target Tasks","created":"2025-07-16","cited_by_count":19,"area":null},{"id":"2406.19292","title":"From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data","created":"2024-06-27","cited_by_count":18,"area":"lr"},{"id":"2410.03735","title":"Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling","created":"2024-09-30","cited_by_count":18,"area":null},{"id":"2504.17119","title":"The Rise of Small Language Models in Healthcare: A Comprehensive Survey","created":"2025-04-23","cited_by_count":18,"area":null},{"id":"2409.04828","title":"POINTS: Improving Your Vision-language Model with Affordable Strategies","created":"2024-09-07","cited_by_count":17,"area":"mllm"},{"id":"2411.07133","title":"Stronger Models are NOT Stronger Teachers for Instruction Tuning","created":"2024-11-11","cited_by_count":16,"area":null},{"id":"2407.08583","title":"The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective","created":"2024-07-11","cited_by_count":15,"area":"mllm"},{"id":"2410.18779","title":"A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2510.16882","title":"Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning","created":"2025-10-19","cited_by_count":15,"area":null},{"id":"2505.13772","title":"Krikri: Advancing Open Large Language Models for Greek","created":"2025-05-19","cited_by_count":14,"area":null},{"id":"2407.16607","title":"Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?","created":"2024-07-23","cited_by_count":13,"area":null},{"id":"2409.19656","title":"Multimodal Misinformation Detection by Learning from Synthetic Data with Multimodal LLMs","created":"2024-09-29","cited_by_count":13,"area":"mllm"},{"id":"2502.14709","title":"Group-Level Data Selection for Efficient Pretraining","created":"2025-02-20","cited_by_count":13,"area":null},{"id":"2505.07437","title":"LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning","created":"2025-05-12","cited_by_count":13,"area":"alignment"},{"id":"2505.17895","title":"DataRater: Meta-Learned Dataset Curation","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2406.14115","title":"Take the essence and discard the dross: A Rethinking on Data Selection for Fine-Tuning Large Language Models","created":"2024-06-20","cited_by_count":12,"area":"lr"},{"id":"2410.03083","title":"Scaling Parameter-Constrained Language Models with Quality Data","created":"2024-10-04","cited_by_count":12,"area":null},{"id":"2410.04715","title":"Selection of LLM Fine-Tuning Data based on Orthogonal Rules","created":"2024-10-07","cited_by_count":12,"area":null},{"id":"2410.16208","title":"Compute-Constrained Data Selection","created":"2024-10-21","cited_by_count":12,"area":null},{"id":"2502.14050","title":"Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder","created":"2025-02-19","cited_by_count":12,"area":"mechinterp"},{"id":"2507.05195","title":"Train-before-Test Harmonizes Language Model Rankings","created":"2025-07-07","cited_by_count":12,"area":null},{"id":"2508.04379","title":"VisionTS++: Cross-Modal Time Series Foundation Model with Continual Pre-trained Vision Backbones","created":"2025-08-06","cited_by_count":12,"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":"2406.16746","title":"The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2407.06380","title":"Data, Data Everywhere: A Guide for Pretraining Dataset Construction","created":"2024-07-08","cited_by_count":11,"area":null},{"id":"2410.15661","title":"Scalable Data Ablation Approximations for Language Models through Modular Training and Merging","created":"2024-10-21","cited_by_count":11,"area":null},{"id":"2502.06604","title":"Do we really have to filter out random noise in pre-training data for language models?","created":"2025-02-10","cited_by_count":11,"area":null},{"id":"2505.20903","title":"Towards Objective Fine-tuning: How LLMs' Prior Knowledge Causes Potential Poor Calibration?","created":"2025-05-27","cited_by_count":11,"area":null},{"id":"2512.05648","title":"Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs","created":"2025-12-05","cited_by_count":11,"area":"safety"},{"id":"2509.16330","title":"Generalizability of Large Language Model-Based Agents: A Comprehensive Survey","created":"2025-09-19","cited_by_count":10,"area":"agents"},{"id":"2510.00492","title":"Rethinking Reward Models for Multi-Domain Test-Time Scaling","created":"2025-10-01","cited_by_count":10,"area":"lr"},{"id":"2510.26122","title":"Reasoning Path Divergence: A New Metric and Curation Strategy to Unlock LLM Diverse Thinking","created":"2025-10-30","cited_by_count":10,"area":"lr"},{"id":"2412.00420","title":"TAROT: Targeted Data Selection via Optimal Transport","created":"2024-11-30","cited_by_count":9,"area":null},{"id":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2504.01400","title":"ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool Learning","created":"2025-04-02","cited_by_count":9,"area":"agents"},{"id":"2505.12534","title":"ChemPile: A 250GB Diverse and Curated Dataset for Chemical Foundation Models","created":"2025-05-18","cited_by_count":9,"area":null},{"id":"2505.22626","title":"SCIZOR: A Self-Supervised Approach to Data Curation for Large-Scale Imitation Learning","created":"2025-05-28","cited_by_count":9,"area":"offlinerl"},{"id":"2504.06536","title":"Lugha-Llama: Adapting Large Language Models for African Languages","created":"2025-04-09","cited_by_count":8,"area":null},{"id":"2505.12762","title":"IDEAL: Data Equilibrium Adaptation for Multi-Capability Language Model Alignment","created":"2025-05-19","cited_by_count":8,"area":"alignment"},{"id":"2505.18513","title":"Enhancing Training Data Attribution with Representational Optimization","created":"2025-05-24","cited_by_count":8,"area":null},{"id":"2506.07675","title":"QUITE: A Query Rewrite System Beyond Rules with LLM Agents","created":"2025-06-09","cited_by_count":8,"area":"agents"},{"id":"2506.21545","title":"Data Efficacy for Language Model Training","created":"2025-06-26","cited_by_count":8,"area":null},{"id":"2508.19999","title":"Linear-Time Demonstration Selection for In-Context Learning via Gradient Estimation","created":"2025-08-27","cited_by_count":8,"area":null},{"id":"2510.03988","title":"The Signal is in the Steps: Local Scoring for Reasoning Data Selection","created":"2025-10-05","cited_by_count":8,"area":"distill"},{"id":"2601.22588","title":"Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry","created":"2026-01-30","cited_by_count":8,"area":"lr"},{"id":"2602.04735","title":"From Data to Behavior: Predicting Unintended Model Behaviors Before Training","created":"2026-02-04","cited_by_count":8,"area":null},{"id":"2605.19407","title":"A Bitter Lesson for Data Filtering","created":"2026-05-19","cited_by_count":8,"area":null},{"id":"2410.22587","title":"Toxicity of the Commons: Curating Open-Source Pre-Training Data","created":"2024-10-29","cited_by_count":7,"area":null},{"id":"2502.00728","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","created":"2025-02-02","cited_by_count":7,"area":null},{"id":"2504.06962","title":"Efficient Self-Supervised Learning for Earth Observation via Dynamic Dataset Curation","created":"2025-04-09","cited_by_count":7,"area":null},{"id":"2505.16066","title":"Merge to Mix: Mixing Datasets via Model Merging","created":"2025-05-21","cited_by_count":7,"area":null},{"id":"2507.16178","title":"LLM Data Selection and Utilization via Dynamic Bi-level Optimization","created":"2025-07-22","cited_by_count":7,"area":null},{"id":"2511.10721","title":"Fast Data Attribution for Text-to-Image Models","created":"2025-11-13","cited_by_count":7,"area":"diffusion"}],"next_cursor":"100"}