{"total":75,"rows":[{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344,"area":null},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125,"area":null},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658,"area":null},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401,"area":null},{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387,"area":null},{"id":"2309.11235","title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","created":"2023-09-20","cited_by_count":252,"area":null},{"id":"2312.15166","title":"SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling","created":"2023-12-23","cited_by_count":172,"area":null},{"id":"2405.16833","title":"Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models","created":"2024-05-27","cited_by_count":125,"area":null},{"id":"2410.20290","title":"Fast Best-of-N Decoding via Speculative Rejection","created":"2024-10-26","cited_by_count":112,"area":null},{"id":"2308.07074","title":"#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models","created":"2023-08-14","cited_by_count":109,"area":null},{"id":"2308.01862","title":"Wider and Deeper LLM Networks are Fairer LLM Evaluators","created":"2023-08-03","cited_by_count":94,"area":null},{"id":"2409.01586","title":"Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation","created":"2024-09-03","cited_by_count":92,"area":null},{"id":"2308.12833","title":"Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities","created":"2023-08-24","cited_by_count":82,"area":null},{"id":"2305.14239","title":"On Learning to Summarize with Large Language Models as References","created":"2023-05-23","cited_by_count":80,"area":null},{"id":"2506.09033","title":"Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning","created":"2025-06-10","cited_by_count":72,"area":null},{"id":"2307.14936","title":"PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback","created":"2023-07-27","cited_by_count":69,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2311.10766","title":"Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values","created":"2023-11-15","cited_by_count":50,"area":null},{"id":"2305.13246","title":"Interactive Natural Language Processing","created":"2023-05-22","cited_by_count":31,"area":null},{"id":"2503.08625","title":"SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories","created":"2025-03-11","cited_by_count":30,"area":null},{"id":"2310.11053","title":"Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning","created":"2023-10-17","cited_by_count":26,"area":null},{"id":"2407.10627","title":"Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arena","created":"2024-07-15","cited_by_count":26,"area":null},{"id":"2407.04118","title":"MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization","created":"2024-07-04","cited_by_count":21,"area":null},{"id":"2501.18100","title":"Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation","created":"2025-01-30","cited_by_count":20,"area":null},{"id":"2410.03837","title":"Learning Code Preference via Synthetic Evolution","created":"2024-10-04","cited_by_count":19,"area":null},{"id":"2506.08473","title":"AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin","created":"2025-06-10","cited_by_count":19,"area":null},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2407.02272","title":"Aligning Human Motion Generation with Human Perceptions","created":"2024-07-02","cited_by_count":16,"area":null},{"id":"2411.11504","title":"Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering","created":"2024-11-18","cited_by_count":16,"area":null},{"id":"2311.16989","title":"ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?","created":"2023-11-28","cited_by_count":15,"area":null},{"id":"2310.02527","title":"CITING: Large Language Models Create Curriculum for Instruction Tuning","created":"2023-10-04","cited_by_count":14,"area":null},{"id":"2404.01342","title":"DiffAgent: Fast and Accurate Text-to-Image API Selection with Large Language Model","created":"2024-03-31","cited_by_count":12,"area":null},{"id":"2305.11366","title":"AutoTrial: Prompting Language Models for Clinical Trial Design","created":"2023-05-19","cited_by_count":11,"area":null},{"id":"2609.00196","title":"WHALE: A Simple Recipe for Joint Harness-Weight Optimization","created":"2026-08-31","cited_by_count":11,"area":null},{"id":"2410.23074","title":"Multi-Programming Language Sandbox for LLMs","created":"2024-10-30","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":"2310.17551","title":"Unpacking the Ethical Value Alignment in Big Models","created":"2023-10-26","cited_by_count":9,"area":null},{"id":"2407.12022","title":"ITERTL: An Iterative Framework for Fine-tuning LLMs for RTL Code Generation","created":"2024-06-28","cited_by_count":9,"area":null},{"id":"2312.05657","title":"PerfRL: A Small Language Model Framework for Efficient Code Optimization","created":"2023-12-09","cited_by_count":8,"area":null},{"id":"2404.09445","title":"Exploring Text-to-Motion Generation with Human Preference","created":"2024-04-15","cited_by_count":8,"area":null},{"id":"2310.02263","title":"Automatic Pair Construction for Contrastive Post-training","created":"2023-10-03","cited_by_count":7,"area":null},{"id":"2310.05857","title":"Improving Summarization with Human Edits","created":"2023-10-09","cited_by_count":7,"area":null},{"id":"2411.00412","title":"Adapting While Learning: Grounding LLMs for Scientific Problems with Intelligent Tool Usage Adaptation","created":"2024-11-01","cited_by_count":7,"area":null},{"id":"2506.11430","title":"Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference Optimization","created":"2025-06-13","cited_by_count":7,"area":null},{"id":"2312.01057","title":"RLHF and IIA: Perverse Incentives","created":"2023-12-02","cited_by_count":6,"area":null},{"id":"2401.12292","title":"GRATH: Gradual Self-Truthifying for Large Language Models","created":"2024-01-22","cited_by_count":6,"area":null},{"id":"2405.06424","title":"Improving Instruction Following in Language Models through Proxy-Based Uncertainty Estimation","created":"2024-05-10","cited_by_count":6,"area":null},{"id":"2410.12893","title":"MIRROR: A Novel Approach for the Automated Evaluation of Open-Ended Question Generation","created":"2024-10-16","cited_by_count":6,"area":null},{"id":"2411.10681","title":"Structured Dialogue System for Mental Health: An LLM Chatbot Leveraging the PM+ Guidelines","created":"2024-11-16","cited_by_count":6,"area":null},{"id":"2502.07237","title":"DrugImproverGPT: A Large Language Model for Drug Optimization with Fine-Tuning via Structured Policy Optimization","created":"2025-02-11","cited_by_count":6,"area":null},{"id":"2510.17881","title":"POPI: Personalizing LLMs via Optimized Natural Language Preference Inference","created":"2025-10-17","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2312.17055","title":"Beyond Output Matching: Bidirectional Alignment for Enhanced In-Context Learning","created":"2023-12-28","cited_by_count":5,"area":null},{"id":"2409.07131","title":"Reranking Laws for Language Generation: A Communication-Theoretic Perspective","created":"2024-09-11","cited_by_count":4,"area":null},{"id":"2410.13957","title":"Goal Inference from Open-Ended Dialog","created":"2024-10-17","cited_by_count":4,"area":null},{"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":"2506.16024","title":"From General to Targeted Rewards: Surpassing GPT-4 in Open-Ended Long-Context Generation","created":"2025-06-19","cited_by_count":4,"area":null},{"id":"2510.19296","title":"QiMeng-SALV: Signal-Aware Learning for Verilog Code Generation","created":"2025-10-22","cited_by_count":4,"area":null},{"id":"2512.00319","title":"RL-Struct: A Lightweight Reinforcement Learning Framework for Reliable Structured Output in LLMs","created":"2025-11-29","cited_by_count":3,"area":null},{"id":"2305.11991","title":"Evaluation of medium-large Language Models at zero-shot closed book generative question answering","created":"2023-05-19","cited_by_count":2,"area":null},{"id":"2310.08899","title":"Exploration with Principles for Diverse AI Supervision","created":"2023-10-13","cited_by_count":2,"area":null},{"id":"2506.08188","title":"GradEscape: A Gradient-Based Evader Against AI-Generated Text Detectors","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2605.06901","title":"Reflections and New Directions for Human-Centered Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.28272","title":"EchoAvatar: Real-time Generative Avatar Animation from Audio Streams","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2310.13028","title":"Reliable Academic Conference Question Answering: A Study Based on Large Language Model","created":"2023-10-19","cited_by_count":1,"area":null},{"id":"2502.15616","title":"Pastiche Novel Generation Creating: Fan Fiction You Love in Your Favorite Author's Style","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2512.15009","title":"Model Agnostic Preference Optimization for Medical Image Segmentation","created":"2025-12-17","cited_by_count":1,"area":null},{"id":"2605.26442","title":"Alignment Tuning for Large Language Models: A Data-Centric Lens on Alignment Data Pipelines","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2307.00266","title":"Hierarchical Pretraining for Biomedical Term Embeddings","created":"2023-07-01","cited_by_count":0,"area":null},{"id":"2511.21762","title":"Factors That Support Grounded Responses in LLM Conversations: A Rapid Review","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2606.00544","title":"Escaping the Mode Lottery: Multi-Response Training Improves Language Model Generalization","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.01436","title":"Learning from Saturated Data: Signals Beyond Correctness for LLM Training","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2608.15107","title":"Global Federated Learning Strategies for Building Efficient Personalized Models","created":"2026-08-15","cited_by_count":0,"area":null}],"next_cursor":null}