{"total":58,"rows":[{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2402.05123","title":"A Survey on Data Selection for LLM Instruction Tuning","created":"2024-02-04","cited_by_count":77,"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":"2307.08674","title":"TableGPT: Towards Unifying Tables, Nature Language and Commands into One GPT","created":"2023-07-17","cited_by_count":59,"area":null},{"id":"2308.12014","title":"From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models","created":"2023-08-23","cited_by_count":45,"area":"alignment"},{"id":"2402.18243","title":"Learning or Self-aligning? Rethinking Instruction Fine-tuning","created":"2024-02-28","cited_by_count":43,"area":"lr"},{"id":"2312.14187","title":"WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning","created":"2023-12-20","cited_by_count":42,"area":null},{"id":"2410.10014","title":"Safety-Aware Fine-Tuning of Large Language Models","created":"2024-10-13","cited_by_count":34,"area":null},{"id":"2407.15235","title":"TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data","created":"2024-07-21","cited_by_count":30,"area":null},{"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":"2504.11914","title":"AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detection","created":"2025-04-16","cited_by_count":28,"area":"lr"},{"id":"2311.14904","title":"LLM-Assisted Code Cleaning For Training Accurate Code Generators","created":"2023-11-25","cited_by_count":27,"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":"2312.17653","title":"LARP: Language-Agent Role Play for Open-World Games","created":"2023-12-24","cited_by_count":24,"area":"agents"},{"id":"2502.17184","title":"Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric","created":"2025-02-24","cited_by_count":24,"area":null},{"id":"2404.07900","title":"High-Dimension Human Value Representation in Large Language Models","created":"2024-04-11","cited_by_count":20,"area":null},{"id":"2402.17355","title":"RECOST: External Knowledge Guided Data-efficient Instruction Tuning","created":"2024-02-27","cited_by_count":18,"area":null},{"id":"2402.19465","title":"Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models","created":"2024-02-29","cited_by_count":18,"area":null},{"id":"2312.01700","title":"Data Management For Training Large Language Models: A Survey","created":"2023-12-04","cited_by_count":17,"area":null},{"id":"2403.08370","title":"SMART: Submodular Data Mixture Strategy for Instruction Tuning","created":"2024-03-13","cited_by_count":17,"area":null},{"id":"2504.16420","title":"A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigms","created":"2025-04-23","cited_by_count":17,"area":"agents"},{"id":"2401.16553","title":"SelectLLM: Can LLMs Select Important Instructions to Annotate?","created":"2024-01-29","cited_by_count":16,"area":null},{"id":"2307.03692","title":"Becoming self-instruct: introducing early stopping criteria for minimal instruct tuning","created":"2023-07-05","cited_by_count":13,"area":"synth"},{"id":"2508.12680","title":"Vision-G1: Towards General Vision Language Reasoning with Multi-Domain Data Curation","created":"2025-08-18","cited_by_count":13,"area":"lr"},{"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":"2509.08269","title":"A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solving","created":"2025-09-10","cited_by_count":11,"area":null},{"id":"2602.08499","title":"Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards","created":"2026-02-09","cited_by_count":11,"area":"lr"},{"id":"2410.10926","title":"Federated Data-Efficient Instruction Tuning for Large Language Models","created":"2024-10-14","cited_by_count":10,"area":null},{"id":"2308.12711","title":"Harnessing the Power of David against Goliath: Exploring Instruction Data Generation without Using Closed-Source Models","created":"2023-08-24","cited_by_count":6,"area":null},{"id":"2310.13008","title":"DavIR: Data Selection via Implicit Reward for Large Language Models","created":"2023-10-16","cited_by_count":6,"area":"alignment"},{"id":"2410.13464","title":"IterSelectTune: An Iterative Training Framework for Efficient Instruction-Tuning Data Selection","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2410.14940","title":"Baichuan Alignment Technical Report","created":"2024-10-19","cited_by_count":6,"area":"alignment"},{"id":"2508.17184","title":"Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models","created":"2025-08-24","cited_by_count":5,"area":"alignment"},{"id":"2411.09539","title":"Fine-tuning Large Language Models with Limited Data: A Survey and Practical Guide","created":"2024-11-14","cited_by_count":4,"area":null},{"id":"2508.04329","title":"Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning","created":"2025-08-06","cited_by_count":4,"area":null},{"id":"2601.10348","title":"Training-Trajectory-Aware Token Selection","created":"2026-01-15","cited_by_count":4,"area":"lr"},{"id":"2602.14696","title":"A Critical Look at Targeted Instruction Selection: Disentangling What Matters (and What Doesn't)","created":"2026-02-16","cited_by_count":4,"area":null},{"id":"2411.00005","title":"Mastering the Craft of Data Synthesis for CodeLLMs","created":"2024-10-16","cited_by_count":3,"area":"synth"},{"id":"2411.03768","title":"A Bayesian Approach to Data Point Selection","created":"2024-11-06","cited_by_count":3,"area":null},{"id":"2310.19462","title":"Constituency Parsing using LLMs","created":"2023-10-30","cited_by_count":2,"area":null},{"id":"2408.15915","title":"Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models","created":"2024-08-28","cited_by_count":2,"area":"moe"},{"id":"2409.18541","title":"Align$^2$LLaVA: Cascaded Human and Large Language Model Preference Alignment for Multi-modal Instruction Curation","created":"2024-09-27","cited_by_count":2,"area":"mllm"},{"id":"2410.20791","title":"From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap","created":"2024-10-28","cited_by_count":2,"area":null},{"id":"2505.18799","title":"ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models","created":"2025-05-24","cited_by_count":2,"area":"alignment"},{"id":"2509.06524","title":"LAMDAS: LLM as an Implicit Classifier for Domain-specific Data Selection","created":"2025-09-08","cited_by_count":2,"area":null},{"id":"2410.11540","title":"Data Quality Control in Federated Instruction-tuning of Large Language Models","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2506.15702","title":"Minifinetuning: Low-Data Generation Domain Adaptation through Corrective Self-Distillation","created":"2025-05-30","cited_by_count":1,"area":"distill"},{"id":"2604.17650","title":"Measuring Distribution Shift in User Prompts and Its Effects on LLM Performance","created":"2026-04-19","cited_by_count":1,"area":null},{"id":"2609.39183","title":"Aligning Thoughts with Answers: Probability Rewards to Tame Thinking Drift","created":"2026-09-30","cited_by_count":1,"area":"lr"},{"id":"2501.07674","title":"CDS: Knowledge Component-Driven Data Synthesis Guided by Cognitive Diagnosis Theory","created":"2025-01-13","cited_by_count":0,"area":"synth"},{"id":"2505.17632","title":"ReqBrain: Task-Specific Instruction Tuning of LLMs for AI-Assisted Requirements Generation","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2506.09329","title":"Towards Efficient and Effective Alignment of Large Language Models","created":"2025-06-11","cited_by_count":0,"area":"alignment"},{"id":"2507.03673","title":"TACOS: Open Tagging and Comparative Scoring for Instruction Fine-Tuning Data Selection","created":"2025-07-04","cited_by_count":0,"area":"alignment"},{"id":"2509.18585","title":"TsqLoRA: Towards Sensitivity and Quality Low-Rank Adaptation for Efficient Fine-Tuning","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2605.07488","title":"Efficient Data Selection for Multimodal Models via Incremental Optimization Utility","created":"2026-05-08","cited_by_count":0,"area":"mllm"},{"id":"2605.30857","title":"MADS: Model-Aware Diverse Core Set Selection for Instruction Tuning","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2610.02593","title":"Fisher-Guided Submodular Data Selection for Continual Pre-Training of Large Language Models","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}