{"total":379,"rows":[{"id":"2306.13649","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","created":"2023-06-23","cited_by_count":939,"area":"synth"},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712,"area":"mllm"},{"id":"2308.09583","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","created":"2023-08-18","cited_by_count":625,"area":"lr"},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623,"area":null},{"id":"2306.11644","title":"Textbooks Are All You Need","created":"2023-06-20","cited_by_count":569,"area":null},{"id":"2403.02691","title":"InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents","created":"2024-03-05","cited_by_count":538,"area":"agents"},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532,"area":null},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525,"area":null},{"id":"2309.05653","title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","created":"2023-09-11","cited_by_count":487,"area":null},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2309.13007","title":"ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs","created":"2023-09-22","cited_by_count":309,"area":"lr"},{"id":"2401.00368","title":"Improving Text Embeddings with Large Language Models","created":"2023-12-31","cited_by_count":303,"area":null},{"id":"2512.13564","title":"Memory in the Age of AI Agents","created":"2025-12-15","cited_by_count":303,"area":"agents"},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2311.04076","title":"Do LLMs exhibit human-like response biases? A case study in survey design","created":"2023-11-07","cited_by_count":180,"area":null},{"id":"2311.11045","title":"Orca 2: Teaching Small Language Models How to Reason","created":"2023-11-18","cited_by_count":159,"area":null},{"id":"2402.14830","title":"Orca-Math: Unlocking the potential of SLMs in Grade School Math","created":"2024-02-16","cited_by_count":151,"area":"lr"},{"id":"2504.21318","title":"Phi-4-reasoning Technical Report","created":"2025-04-30","cited_by_count":151,"area":"lr"},{"id":"2308.07317","title":"Platypus: Quick, Cheap, and Powerful Refinement of LLMs","created":"2023-08-14","cited_by_count":150,"area":null},{"id":"2404.00610","title":"RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation","created":"2024-03-31","cited_by_count":147,"area":"rag"},{"id":"2402.10176","title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","created":"2024-02-15","cited_by_count":143,"area":"lr"},{"id":"2403.03883","title":"SaulLM-7B: A pioneering Large Language Model for Law","created":"2024-03-06","cited_by_count":142,"area":null},{"id":"2309.01446","title":"Open Sesame! Universal Black Box Jailbreaking of Large Language Models","created":"2023-09-04","cited_by_count":134,"area":"safety"},{"id":"2510.07743","title":"OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment","created":"2025-10-09","cited_by_count":132,"area":"alignment"},{"id":"2404.03648","title":"AutoWebGLM: A Large Language Model-based Web Navigating Agent","created":"2024-04-04","cited_by_count":130,"area":"agents"},{"id":"2402.06954","title":"OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning","created":"2024-02-10","cited_by_count":128,"area":null},{"id":"2409.11402","title":"NVLM: Open Frontier-Class Multimodal LLMs","created":"2024-09-17","cited_by_count":125,"area":"mllm"},{"id":"2311.04205","title":"Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves","created":"2023-11-07","cited_by_count":123,"area":null},{"id":"2308.10204","title":"ChatEDA: A Large Language Model Powered Autonomous Agent for EDA","created":"2023-08-20","cited_by_count":122,"area":"agents"},{"id":"2412.11664","title":"C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness","created":"2024-12-16","cited_by_count":119,"area":"lr"},{"id":"2406.07933","title":"Large Language Model Unlearning via Embedding-Corrupted Prompts","created":"2024-06-12","cited_by_count":116,"area":"safety"},{"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":"2402.01761","title":"Rethinking Interpretability in the Era of Large Language Models","created":"2024-01-30","cited_by_count":111,"area":"lr"},{"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":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106,"area":"synth"},{"id":"2312.00738","title":"SeaLLMs -- Large Language Models for Southeast Asia","created":"2023-12-01","cited_by_count":104,"area":null},{"id":"2402.13064","title":"Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models","created":"2024-02-20","cited_by_count":99,"area":"synth"},{"id":"2402.18540","title":"Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates","created":"2024-02-28","cited_by_count":96,"area":null},{"id":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90,"area":"alignment"},{"id":"2407.03502","title":"AgentInstruct: Toward Generative Teaching with Agentic Flows","created":"2024-07-03","cited_by_count":89,"area":"agents"},{"id":"2402.19464","title":"Curiosity-driven Red-teaming for Large Language Models","created":"2024-02-29","cited_by_count":88,"area":"safety"},{"id":"2402.04833","title":"Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning","created":"2024-02-07","cited_by_count":85,"area":"alignment"},{"id":"2405.17977","title":"Aligning to Thousands of Preferences via System Message Generalization","created":"2024-05-28","cited_by_count":84,"area":"alignment"},{"id":"2402.09345","title":"InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling","created":"2024-02-14","cited_by_count":79,"area":"alignment"},{"id":"2412.15084","title":"AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling","created":"2024-12-19","cited_by_count":77,"area":"lr"},{"id":"2310.06830","title":"Lemur: Harmonizing Natural Language and Code for Language Agents","created":"2023-10-10","cited_by_count":72,"area":"agents"},{"id":"2403.15042","title":"LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement","created":"2024-03-22","cited_by_count":70,"area":null},{"id":"2309.09150","title":"Can Large Language Models Understand Real-World Complex Instructions?","created":"2023-09-17","cited_by_count":69,"area":null},{"id":"2408.01122","title":"CFBench: A Comprehensive Constraints-Following Benchmark for LLMs","created":"2024-08-02","cited_by_count":67,"area":null},{"id":"2410.07471","title":"SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection","created":"2024-10-09","cited_by_count":64,"area":null},{"id":"2309.02144","title":"Making Large Language Models Better Reasoners with Alignment","created":"2023-09-05","cited_by_count":63,"area":"lr"},{"id":"2404.14662","title":"NExT: Teaching Large Language Models to Reason about Code Execution","created":"2024-04-23","cited_by_count":63,"area":"lr"},{"id":"2408.16737","title":"Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling","created":"2024-08-29","cited_by_count":61,"area":"lr"},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59,"area":"safety"},{"id":"2310.05707","title":"Guiding Language Model Reasoning with Planning Tokens","created":"2023-10-09","cited_by_count":58,"area":"lr"},{"id":"2402.14904","title":"Watermarking Makes Language Models Radioactive","created":"2024-02-22","cited_by_count":58,"area":"safety"},{"id":"2403.09032","title":"CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences","created":"2024-03-14","cited_by_count":57,"area":"alignment"},{"id":"2406.00222","title":"Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training","created":"2024-05-31","cited_by_count":57,"area":"alignment"},{"id":"2310.05910","title":"SALMON: Self-Alignment with Instructable Reward Models","created":"2023-10-09","cited_by_count":55,"area":"alignment"},{"id":"2408.07990","title":"FuseChat: Knowledge Fusion of Chat Models","created":"2024-08-15","cited_by_count":55,"area":null},{"id":"2401.01523","title":"GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse","created":"2024-01-03","cited_by_count":52,"area":null},{"id":"2309.09530","title":"Adapting Large Language Models to Domains via Reading Comprehension","created":"2023-09-18","cited_by_count":50,"area":null},{"id":"2505.17612","title":"Distilling LLM Agent into Small Models with Retrieval and Code Tools","created":"2025-05-23","cited_by_count":47,"area":"lr"},{"id":"2406.01940","title":"Process-Driven Autoformalization in Lean 4","created":"2024-06-04","cited_by_count":45,"area":"lr"},{"id":"2408.15881","title":"LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation","created":"2024-08-28","cited_by_count":45,"area":"mllm"},{"id":"2310.10632","title":"BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in Biology","created":"2023-10-16","cited_by_count":43,"area":null},{"id":"2402.01620","title":"MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models","created":"2024-02-02","cited_by_count":43,"area":"lr"},{"id":"2402.10379","title":"DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows","created":"2024-02-16","cited_by_count":43,"area":"synth"},{"id":"2412.13337","title":"Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs","created":"2024-12-17","cited_by_count":40,"area":null},{"id":"2311.08711","title":"PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning","created":"2023-11-15","cited_by_count":39,"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":"2506.20923","title":"KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model","created":"2025-06-26","cited_by_count":36,"area":null},{"id":"2605.10999","title":"SkillGen: Verified Inference-Time Agent Skill Synthesis","created":"2026-05-09","cited_by_count":36,"area":"agents"},{"id":"2311.04072","title":"Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment","created":"2023-11-07","cited_by_count":35,"area":"alignment"},{"id":"2406.10323","title":"GenQA: Generating Millions of Instructions from a Handful of Prompts","created":"2024-06-14","cited_by_count":35,"area":null},{"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":"2402.10614","title":"Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements","created":"2024-02-16","cited_by_count":34,"area":null},{"id":"2402.16705","title":"SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection","created":"2024-02-26","cited_by_count":34,"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":"2308.05696","title":"A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment","created":"2023-08-10","cited_by_count":33,"area":"alignment"},{"id":"2412.03679","title":"Evaluating Language Models as Synthetic Data Generators","created":"2024-12-04","cited_by_count":33,"area":"synth"},{"id":"2307.12966","title":"Aligning Large Language Models with Human: A Survey","created":"2023-07-24","cited_by_count":32,"area":"alignment"},{"id":"2405.13769","title":"Do Language Models Enjoy Their Own Stories? Prompting Large Language Models for Automatic Story Evaluation","created":"2024-05-22","cited_by_count":32,"area":null},{"id":"2406.02657","title":"Block Transformer: Global-to-Local Language Modeling for Fast Inference","created":"2024-06-04","cited_by_count":32,"area":"inference"},{"id":"2502.12197","title":"A Closer Look at System Prompt Robustness","created":"2025-02-15","cited_by_count":32,"area":"safety"},{"id":"2310.06827","title":"Teaching Language Models to Hallucinate Less with Synthetic Tasks","created":"2023-10-10","cited_by_count":31,"area":null},{"id":"2310.11244","title":"Entity Matching using Large Language Models","created":"2023-10-17","cited_by_count":31,"area":null},{"id":"2404.10346","title":"Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards","created":"2024-04-16","cited_by_count":31,"area":"lr"},{"id":"2312.02436","title":"MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following","created":"2023-12-05","cited_by_count":30,"area":null},{"id":"2403.09057","title":"A Continued Pretrained LLM Approach for Automatic Medical Note Generation","created":"2024-03-14","cited_by_count":30,"area":null},{"id":"2405.16802","title":"AutoPSV: Automated Process-Supervised Verifier","created":"2024-05-27","cited_by_count":30,"area":"lr"},{"id":"2406.13975","title":"MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs","created":"2024-06-20","cited_by_count":30,"area":"lr"},{"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":"2506.14728","title":"AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes","created":"2025-06-17","cited_by_count":30,"area":"agents"},{"id":"2402.02318","title":"Diversity Measurement and Subset Selection for Instruction Tuning Datasets","created":"2024-02-04","cited_by_count":29,"area":null},{"id":"2411.19865","title":"Reverse Thinking Makes LLMs Stronger Reasoners","created":"2024-11-29","cited_by_count":29,"area":"lr"},{"id":"2405.07490","title":"Strategic Data Ordering: Enhancing Large Language Model Performance through Curriculum Learning","created":"2024-05-13","cited_by_count":28,"area":null},{"id":"2408.10943","title":"SysBench: Can Large Language Models Follow System Messages?","created":"2024-08-20","cited_by_count":28,"area":null},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"}],"next_cursor":"100"}