{"total":110,"rows":[{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120,"area":null},{"id":"2403.04652","title":"Yi: Open Foundation Models by 01.AI","created":"2024-03-07","cited_by_count":719,"area":null},{"id":"2402.01364","title":"Continual Learning for Large Language Models: A Survey","created":"2024-02-02","cited_by_count":147,"area":null},{"id":"2401.02415","title":"LLaMA Pro: Progressive LLaMA with Block Expansion","created":"2024-01-04","cited_by_count":101,"area":null},{"id":"2405.03644","title":"When LLMs Meet Cybersecurity: A Systematic Literature Review","created":"2024-05-06","cited_by_count":71,"area":null},{"id":"2407.15186","title":"A Survey on Employing Large Language Models for Text-to-SQL Tasks","created":"2024-07-21","cited_by_count":67,"area":null},{"id":"2401.10334","title":"DrugAssist: A Large Language Model for Molecule Optimization","created":"2023-12-28","cited_by_count":59,"area":null},{"id":"2402.16117","title":"RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis","created":"2024-02-25","cited_by_count":58,"area":null},{"id":"2402.18191","title":"Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation","created":"2024-02-28","cited_by_count":53,"area":null},{"id":"2502.12446","title":"Multi-Attribute Steering of Language Models via Targeted Intervention","created":"2025-02-18","cited_by_count":46,"area":null},{"id":"2406.07835","title":"SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature","created":"2024-06-10","cited_by_count":41,"area":null},{"id":"2406.16797","title":"Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs","created":"2024-06-24","cited_by_count":31,"area":null},{"id":"2406.08587","title":"CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery","created":"2024-06-12","cited_by_count":30,"area":null},{"id":"2310.11616","title":"Evidence of interrelated cognitive-like capabilities in large language models: Indications of artificial general intelligence or achievement?","created":"2023-10-17","cited_by_count":27,"area":null},{"id":"2402.11893","title":"Discerning and Resolving Knowledge Conflicts through Adaptive Decoding with Contextual Information-Entropy Constraint","created":"2024-02-19","cited_by_count":27,"area":null},{"id":"2310.06504","title":"Revisit Input Perturbation Problems for LLMs: A Unified Robustness Evaluation Framework for Noisy Slot Filling Task","created":"2023-10-10","cited_by_count":23,"area":null},{"id":"2401.07004","title":"Extending LLMs' Context Window with 100 Samples","created":"2024-01-13","cited_by_count":21,"area":null},{"id":"2412.11919","title":"RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation","created":"2024-12-16","cited_by_count":20,"area":null},{"id":"2504.07448","title":"LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation","created":"2025-04-10","cited_by_count":19,"area":null},{"id":"2404.18466","title":"HFT: Half Fine-Tuning for Large Language Models","created":"2024-04-29","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":"2402.01909","title":"On Catastrophic Inheritance of Large Foundation Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2409.07045","title":"Beyond IID: Optimizing Instruction Learning from the Perspective of Instruction Interaction and Dependency","created":"2024-09-11","cited_by_count":13,"area":null},{"id":"2411.11027","title":"BianCang: A Traditional Chinese Medicine Large Language Model","created":"2024-11-17","cited_by_count":12,"area":null},{"id":"2504.13835","title":"MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space","created":"2025-04-18","cited_by_count":12,"area":null},{"id":"2506.03483","title":"APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training","created":"2025-06-04","cited_by_count":12,"area":null},{"id":"2508.11953","title":"Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models","created":"2025-08-16","cited_by_count":12,"area":null},{"id":"2603.01097","title":"Understanding LoRA as Knowledge Memory: An Empirical Analysis","created":"2026-03-01","cited_by_count":12,"area":null},{"id":"2402.09136","title":"DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning","created":"2024-02-14","cited_by_count":11,"area":null},{"id":"2408.08343","title":"API-guided Dataset Synthesis to Finetune Large Code Models","created":"2024-08-15","cited_by_count":11,"area":null},{"id":"2404.16766","title":"Prefix Text as a Yarn: Eliciting Non-English Alignment in Foundation Language Model","created":"2024-04-25","cited_by_count":10,"area":null},{"id":"2512.13674","title":"Towards Interactive Intelligence for Digital Humans","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2509.21044","title":"Reinforcement Learning Fine-Tuning Enhances Activation Intensity and Diversity in the Internal Circuitry of LLMs","created":"2025-09-25","cited_by_count":9,"area":null},{"id":"2402.08015","title":"Walia-LLM: Enhancing Amharic-LLaMA by Integrating Task-Specific and Generative Datasets","created":"2024-02-12","cited_by_count":8,"area":null},{"id":"2409.03810","title":"How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality Data","created":"2024-09-05","cited_by_count":8,"area":null},{"id":"2410.04717","title":"$\\textbf{Only-IF}$:Revealing the Decisive Effect of Instruction Diversity on Generalization","created":"2024-10-07","cited_by_count":8,"area":null},{"id":"2604.10079","title":"Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models","created":"2026-04-11","cited_by_count":8,"area":null},{"id":"2408.04556","title":"BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models","created":"2024-08-08","cited_by_count":7,"area":null},{"id":"2509.16596","title":"Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels","created":"2025-09-20","cited_by_count":7,"area":null},{"id":"2602.21992","title":"PanoEnv: Exploring 3D Spatial Intelligence in Panoramic Environments with Reinforcement Learning","created":"2026-02-25","cited_by_count":7,"area":null},{"id":"2405.19265","title":"AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data","created":"2024-05-29","cited_by_count":6,"area":null},{"id":"2507.10605","title":"RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services","created":"2025-07-13","cited_by_count":6,"area":null},{"id":"2406.01392","title":"Sparsity-Accelerated Training for Large Language Models","created":"2024-06-03","cited_by_count":5,"area":null},{"id":"2408.08003","title":"Leveraging Web-Crawled Data for High-Quality Fine-Tuning","created":"2024-08-15","cited_by_count":5,"area":null},{"id":"2409.15820","title":"Supervised Fine-Tuning Achieve Rapid Task Adaption Via Alternating Attention Head Activation Patterns","created":"2024-09-24","cited_by_count":5,"area":null},{"id":"2412.07405","title":"MoDULA: Mixture of Domain-Specific and Universal LoRA for Multi-Task Learning","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2505.12814","title":"PsyMem: Fine-grained psychological alignment and Explicit Memory Control for Advanced Role-Playing LLMs","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2601.13240","title":"KOCO-BENCH: Can Large Language Models Leverage Domain Knowledge in Software Development?","created":"2026-01-19","cited_by_count":5,"area":null},{"id":"2401.06792","title":"LightHouse: A Survey of AGI Hallucination","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2402.11279","title":"Multi-Perspective Consistency Enhances Confidence Estimation in Large Language Models","created":"2024-02-17","cited_by_count":4,"area":null},{"id":"2405.16579","title":"Automatically Generating Numerous Context-Driven SFT Data for LLMs across Diverse Granularity","created":"2024-05-26","cited_by_count":4,"area":null},{"id":"2410.16088","title":"Fine-Tuning LLMs for Reliable Medical Question-Answering Services","created":"2024-10-21","cited_by_count":4,"area":null},{"id":"2511.00130","title":"A Comparative Analysis of LLM Adaptation: SFT, LoRA, and ICL in Data-Scarce Scenarios","created":"2025-10-31","cited_by_count":4,"area":null},{"id":"2604.07892","title":"Data Selection for Multi-turn Dialogue Instruction Tuning","created":"2026-04-09","cited_by_count":4,"area":null},{"id":"2605.10770","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2408.05541","title":"P3: A Policy-Driven, Pace-Adaptive, and Diversity-Promoted Framework for data pruning in LLM Training","created":"2024-08-10","cited_by_count":3,"area":null},{"id":"2411.11266","title":"VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs","created":"2024-11-18","cited_by_count":3,"area":null},{"id":"2504.16188","title":"FinNLI: Novel Dataset for Multi-Genre Financial Natural Language Inference Benchmarking","created":"2025-04-22","cited_by_count":3,"area":null},{"id":"2603.21606","title":"mSFT: Addressing Dataset Mixtures Overfitting Heterogeneously in Multi-task SFT","created":"2026-03-23","cited_by_count":3,"area":null},{"id":"2604.18389","title":"Understanding the Prompt Sensitivity","created":"2026-04-20","cited_by_count":3,"area":null},{"id":"2404.00914","title":"Token-Efficient Leverage Learning in Large Language Models","created":"2024-04-01","cited_by_count":2,"area":null},{"id":"2409.15825","title":"60 Data Points are Sufficient to Fine-Tune LLMs for Question-Answering","created":"2024-09-24","cited_by_count":2,"area":null},{"id":"2410.22264","title":"Provable Meta-Learning with Low-Rank Adaptations","created":"2024-10-29","cited_by_count":2,"area":null},{"id":"2410.23472","title":"Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2412.15236","title":"CareBot: A Pioneering Full-Process Open-Source Medical Language Model","created":"2024-12-12","cited_by_count":2,"area":null},{"id":"2503.10668","title":"Identity Lock: Locking API Fine-tuned LLMs With Identity-based Wake Words","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2503.16457","title":"Integrating Personality into Digital Humans: A Review of LLM-Driven Approaches for Virtual Reality","created":"2025-02-22","cited_by_count":2,"area":null},{"id":"2505.12300","title":"HBO: Hierarchical Balancing Optimization for Fine-Tuning Large Language Models","created":"2025-05-18","cited_by_count":2,"area":null},{"id":"2506.10288","title":"ClusterUCB: Efficient Gradient-Based Data Selection for Targeted Fine-Tuning of LLMs","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2507.21099","title":"Rewrite-to-Rank: Optimizing Ad Visibility via Retrieval-Aware Text Rewriting","created":"2025-07-03","cited_by_count":2,"area":null},{"id":"2509.13790","title":"Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learning","created":"2025-09-17","cited_by_count":2,"area":null},{"id":"2604.14010","title":"Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning","created":"2026-04-15","cited_by_count":2,"area":null},{"id":"2405.19787","title":"From Symbolic Tasks to Code Generation: Diversification Yields Better Task Performers","created":"2024-05-30","cited_by_count":1,"area":null},{"id":"2409.14842","title":"HW-TSC's Submission to the CCMT 2024 Machine Translation Tasks","created":"2024-09-23","cited_by_count":1,"area":null},{"id":"2505.22157","title":"LASER: Stratified Selective Sampling for Instruction Tuning with Dedicated Scoring Strategy","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2509.16952","title":"AirQA: A Comprehensive QA Dataset for AI Research with Instance-Level Evaluation","created":"2025-09-21","cited_by_count":1,"area":null},{"id":"2509.18136","title":"From Parameters to Performance: A Data-Driven Study on LLM Structure and Development","created":"2025-09-14","cited_by_count":1,"area":null},{"id":"2510.20001","title":"Beyond MedQA: Towards Real-world Clinical Decision Making in the Era of LLMs","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2510.21894","title":"Understanding Network Behaviors through Natural Language Question-Answering","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2603.08647","title":"Grow, Don't Overwrite: Fine-tuning Without Forgetting","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2604.17184","title":"SynthFix: Adaptive Neuro-Symbolic Code Vulnerability Repair","created":"2026-04-19","cited_by_count":1,"area":null},{"id":"2605.09094","title":"A Tale of Two Problems: Multi-Task Bilevel Learning Meets Equality Constrained Multi-Objective Optimization","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2606.14971","title":"FastMix: Fast Data Mixture Optimization via Gradient Descent","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2402.13866","title":"Kuaiji: the First Chinese Accounting Large Language Model","created":"2024-02-21","cited_by_count":0,"area":null},{"id":"2502.11386","title":"Intelligent Mobile AI-Generated Content Services via Interactive Prompt Engineering and Dynamic Service Provisioning","created":"2025-02-17","cited_by_count":0,"area":null},{"id":"2502.11419","title":"InsBank: Evolving Instruction Subset for Ongoing Alignment","created":"2025-02-17","cited_by_count":0,"area":null},{"id":"2505.15835","title":"Transforming Decoder-Only Transformers for Accurate WiFi-Telemetry Based Indoor Localization","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2509.06463","title":"Accelerate Scaling of LLM Finetuning via Quantifying the Coverage and Depth of Instruction Set","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2510.06039","title":"A Large-Scale Chinese Knowledge Graph-Text Alignment Dataset for Benchmarking Knowledge-Grounded LLMs","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2601.07430","title":"KALE: Enhancing Knowledge Manipulation in Large Language Models via Knowledge-aware Learning","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2601.13995","title":"From Tags to Trees: Structuring Fine-Grained Knowledge for Controllable Data Selection in LLM Instruction Tuning","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2603.17205","title":"OPERA: Online Data Pruning for Efficient Retrieval Model Adaptation","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.01941","title":"Captioning Daily Activity Images in Early Childhood Education: Benchmark and Algorithm","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.06262","title":"From Exposure to Internalization: Dual-Stream Calibration for In-context Clinical Reasoning","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2605.04832","title":"Replay-Based Continual Learning for Physics-Informed Neural Operators","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.12264","title":"Reconstruction of Personally Identifiable Information from Proprietary Data in Supervised Fine-Tuned Models","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.13225","title":"Mix, Don't Tune: Bilingual Pre-Training Outperforms Hyperparameter Search in Data-Constrained Settings","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.19028","title":"Learning When to Adapt","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.21160","title":"Learning First Integrals via Backward-Generated Data and Guided Reinforcement Learning","created":"2026-05-20","cited_by_count":0,"area":null}],"next_cursor":"100"}