{"total":205,"rows":[{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"area":"lr"},{"id":"2501.09686","title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","created":"2025-01-16","cited_by_count":293,"area":"wm"},{"id":"2508.05004","title":"R-Zero: Self-Evolving Reasoning LLM from Zero Data","created":"2025-08-07","cited_by_count":228,"area":"lr"},{"id":"2411.18279","title":"Large Language Model-Brained GUI Agents: A Survey","created":"2024-11-27","cited_by_count":162,"area":"agents"},{"id":"2502.01534","title":"Preference Leakage: A Contamination Problem in LLM-as-a-judge","created":"2025-02-03","cited_by_count":125,"area":null},{"id":"2501.10970","title":"The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs","created":"2025-01-19","cited_by_count":74,"area":null},{"id":"2508.14029","title":"Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR","created":"2025-08-19","cited_by_count":54,"area":"lr"},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2506.08989","title":"SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning","created":"2025-06-10","cited_by_count":42,"area":"lr"},{"id":"2501.02765","title":"Visual Large Language Models for Generalized and Specialized Applications","created":"2025-01-06","cited_by_count":36,"area":"mllm"},{"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":"2411.06469","title":"ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?","created":"2024-11-10","cited_by_count":32,"area":null},{"id":"2502.12378","title":"Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges","created":"2025-02-17","cited_by_count":31,"area":null},{"id":"2505.13975","title":"DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models","created":"2025-05-20","cited_by_count":30,"area":"lr"},{"id":"2510.23587","title":"A Survey of Data Agents: Emerging Paradigm or Overstated Hype?","created":"2025-10-27","cited_by_count":30,"area":"agents"},{"id":"2412.13018","title":"OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain","created":"2024-12-17","cited_by_count":29,"area":"rag"},{"id":"2510.04040","title":"FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning","created":"2025-10-05","cited_by_count":26,"area":"lr"},{"id":"2412.14689","title":"How to Synthesize Text Data without Model Collapse?","created":"2024-12-19","cited_by_count":25,"area":"synth"},{"id":"2506.17784","title":"AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction","created":"2025-06-21","cited_by_count":25,"area":"agents"},{"id":"2502.07942","title":"Symbiotic Cooperation for Web Agents: Harnessing Complementary Strengths of Large and Small LLMs","created":"2025-02-11","cited_by_count":24,"area":"agents"},{"id":"2409.04168","title":"From Calculation to Adjudication: Examining LLM judges on Mathematical Reasoning Tasks","created":"2024-09-06","cited_by_count":22,"area":"lr"},{"id":"2601.03555","title":"SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Models","created":"2026-01-07","cited_by_count":21,"area":"alignment"},{"id":"2412.08467","title":"Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel","created":"2024-12-11","cited_by_count":20,"area":null},{"id":"2412.10136","title":"Can LLMs Convert Graphs to Text-Attributed Graphs?","created":"2024-12-13","cited_by_count":19,"area":null},{"id":"2505.18325","title":"Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary","created":"2025-05-23","cited_by_count":18,"area":"safety"},{"id":"2605.09959","title":"G-Zero: Self-Play for Open-Ended Generation from Zero Data","created":"2026-05-11","cited_by_count":17,"area":"alignment"},{"id":"2602.00521","title":"Diagnosing the Reliability of LLM-as-a-Judge via Item Response Theory","created":"2026-01-31","cited_by_count":16,"area":null},{"id":"2502.11267","title":"Prompting in the Dark: Assessing Human Performance in Prompt Engineering for Data Labeling When Gold Labels Are Absent","created":"2025-02-16","cited_by_count":15,"area":null},{"id":"2503.11411","title":"Empowering Time Series Analysis with Synthetic Data: A Survey and Outlook in the Era of Foundation Models","created":"2025-03-14","cited_by_count":15,"area":"synth"},{"id":"2510.10925","title":"Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation","created":"2025-10-13","cited_by_count":15,"area":"synth"},{"id":"2503.17928","title":"Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization","created":"2025-03-23","cited_by_count":14,"area":"mllm"},{"id":"2601.12294","title":"ToolPRMBench: Evaluating and Advancing Process Reward Models for Tool-using Agents","created":"2026-01-18","cited_by_count":14,"area":"lr"},{"id":"2411.17637","title":"On Limitations of LLM as Annotator for Low Resource Languages","created":"2024-11-26","cited_by_count":12,"area":null},{"id":"2412.14368","title":"Beyond Math: Stories as a Testbed for Memorization-Constrained Reasoning in LLMs","created":"2024-12-18","cited_by_count":12,"area":"lr"},{"id":"2506.06915","title":"Graph Neural Networks in Modern AI-aided Drug Discovery","created":"2025-06-07","cited_by_count":12,"area":null},{"id":"2410.13006","title":"LLM Chain Ensembles for Scalable and Accurate Data Annotation","created":"2024-10-16","cited_by_count":11,"area":null},{"id":"2501.05790","title":"Understanding Impact of Human Feedback via Influence Functions","created":"2025-01-10","cited_by_count":11,"area":"alignment"},{"id":"2605.09253","title":"Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation","created":"2026-05-10","cited_by_count":11,"area":"distill"},{"id":"2503.05587","title":"Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data","created":"2025-03-07","cited_by_count":10,"area":"rag"},{"id":"2506.15629","title":"Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability","created":"2025-06-18","cited_by_count":10,"area":"lr"},{"id":"2509.09969","title":"Large Language Models Meet Legal Artificial Intelligence: A Survey","created":"2025-09-12","cited_by_count":10,"area":null},{"id":"2511.07979","title":"Benchmarking Multi-Step Legal Reasoning and Analyzing Chain-of-Thought Effects in Large Language Models","created":"2025-11-11","cited_by_count":10,"area":"lr"},{"id":"2604.09377","title":"Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios","created":"2026-04-10","cited_by_count":10,"area":"synth"},{"id":"2412.13942","title":"A Rose by Any Other Name: LLM-Generated Explanations Are Good Proxies for Human Explanations to Collect Label Distributions on NLI","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2503.05070","title":"PromptPex: Automatic Test Generation for Language Model Prompts","created":"2025-03-07","cited_by_count":9,"area":null},{"id":"2505.18759","title":"The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation","created":"2025-05-24","cited_by_count":9,"area":"lr"},{"id":"2510.25817","title":"A Survey on Efficient Large Language Model Training: From Data-centric Perspectives","created":"2025-10-29","cited_by_count":9,"area":null},{"id":"2601.08198","title":"Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs","created":"2026-01-13","cited_by_count":9,"area":"synth"},{"id":"2601.17058","title":"Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs","created":"2026-01-22","cited_by_count":9,"area":null},{"id":"2412.07906","title":"Rethinking Emotion Annotations in the Era of Large Language Models","created":"2024-12-10","cited_by_count":8,"area":"lr"},{"id":"2508.05527","title":"AI vs. Human Moderators: A Comparative Evaluation of Multimodal LLMs in Content Moderation for Brand Safety","created":"2025-08-07","cited_by_count":8,"area":"mllm"},{"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":"2502.11735","title":"MT-RAIG: Novel Benchmark and Evaluation Framework for Retrieval-Augmented Insight Generation over Multiple Tables","created":"2025-02-17","cited_by_count":7,"area":"rag"},{"id":"2503.17195","title":"TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning","created":"2025-03-21","cited_by_count":7,"area":null},{"id":"2504.02902","title":"Beyond Accuracy: The Role of Calibration in Self-Improving Large Language Models","created":"2025-04-03","cited_by_count":7,"area":"synth"},{"id":"2505.01903","title":"LookAlike: Consistent Distractor Generation in Math MCQs","created":"2025-05-03","cited_by_count":7,"area":"alignment"},{"id":"2507.07229","title":"SynthTextEval: Synthetic Text Data Generation and Evaluation for High-Stakes Domains","created":"2025-07-09","cited_by_count":7,"area":null},{"id":"2410.13098","title":"A Little Human Data Goes A Long Way","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2411.19638","title":"LLM Teacher-Student Framework for Text Classification With No Manually Annotated Data: A Case Study in IPTC News Topic Classification","created":"2024-11-29","cited_by_count":6,"area":"distill"},{"id":"2502.09897","title":"Artificial Intelligence in Spectroscopy: Advancing Chemistry from Prediction to Generation and Beyond","created":"2025-02-14","cited_by_count":6,"area":null},{"id":"2503.23243","title":"Evaluating how LLM annotations represent diverse views on contentious topics","created":"2025-03-29","cited_by_count":6,"area":null},{"id":"2507.04009","title":"Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents","created":"2025-07-05","cited_by_count":6,"area":null},{"id":"2406.17992","title":"Catching Chameleons: Detecting Evolving Disinformation Generated using Large Language Models","created":"2024-06-26","cited_by_count":5,"area":null},{"id":"2412.14276","title":"Fake News Detection: Comparative Evaluation of BERT-like Models and Large Language Models with Generative AI-Annotated Data","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2506.03857","title":"Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation","created":"2025-06-04","cited_by_count":5,"area":"distill"},{"id":"2506.20274","title":"Enterprise Large Language Model Evaluation Benchmark","created":"2025-06-25","cited_by_count":5,"area":null},{"id":"2505.18458","title":"A Survey of LLM $\\times$ DATA","created":"2025-05-24","cited_by_count":4,"area":"rag"},{"id":"2505.19675","title":"Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinement","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2505.24672","title":"TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis","created":"2025-05-30","cited_by_count":4,"area":"synth"},{"id":"2506.00955","title":"Leveraging Large Language Models for Sarcastic Speech Annotation in Sarcasm Detection","created":"2025-06-01","cited_by_count":4,"area":null},{"id":"2506.01484","title":"LLM in the Loop: Creating the ParaDeHate Dataset for Hate Speech Detoxification","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2510.07169","title":"More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning","created":"2025-10-08","cited_by_count":4,"area":"lr"},{"id":"2511.09833","title":"ACT as Human: Multimodal Large Language Model Data Annotation with Critical Thinking","created":"2025-11-13","cited_by_count":4,"area":"lr"},{"id":"2406.14099","title":"Let Guidelines Guide You: A Prescriptive Guideline-Centered Data Annotation Methodology","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2411.05775","title":"Fact or Fiction? Can LLMs be Reliable Annotators for Political Truths?","created":"2024-11-08","cited_by_count":3,"area":null},{"id":"2412.03796","title":"Automated Multi-Label Annotation for Mental Health Illnesses Using Large Language Models","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2501.13955","title":"Guided Persona-based AI Surveys: Can we replicate personal mobility preferences at scale using LLMs?","created":"2025-01-20","cited_by_count":3,"area":"alignment"},{"id":"2502.12454","title":"Zero-shot Emotion Annotation in Facial Images Using Large Multimodal Models: Benchmarking and Prospects for Multi-Class, Multi-Frame Approaches","created":"2025-02-18","cited_by_count":3,"area":"mllm"},{"id":"2503.03303","title":"SEOE: A Scalable and Reliable Semantic Evaluation Framework for Open Domain Event Detection","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2504.03603","title":"Towards deployment-centric multimodal AI beyond vision and language","created":"2025-04-04","cited_by_count":3,"area":null},{"id":"2504.04024","title":"Window Token Concatenation for Efficient Visual Large Language Models","created":"2025-04-05","cited_by_count":3,"area":null},{"id":"2505.15695","title":"Can Large Language Models be Effective Online Opinion Miners?","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2506.00308","title":"MythTriage: Scalable Detection of Opioid Use Disorder Myths on a Video-Sharing Platform","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2509.06994","title":"VLMs-in-the-Wild: Bridging the Gap Between Academic Benchmarks and Enterprise Reality","created":"2025-09-03","cited_by_count":3,"area":"mllm"},{"id":"2509.12288","title":"Digital Voices of Survival: From Social Media Disclosures to Support Provisions for Domestic Violence Victims","created":"2025-09-15","cited_by_count":3,"area":null},{"id":"2510.14581","title":"Model-agnostic Selective Labeling with Provable Statistical Guarantees","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2510.16549","title":"ReviewGuard: Enhancing Deficient Peer Review Detection via LLM-Driven Data Augmentation","created":"2025-10-18","cited_by_count":3,"area":null},{"id":"2511.08917","title":"\"It's trained by non-disabled people\": Evaluating How Image Quality Affects Product Captioning with Vision-Language Models","created":"2025-11-12","cited_by_count":3,"area":"mllm"},{"id":"2603.15423","title":"Invisible failures in human-AI interactions","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2604.22597","title":"Rethinking Math Reasoning Evaluation: A Robust LLM-as-a-Judge Framework Beyond Symbolic Rigidity","created":"2026-04-24","cited_by_count":3,"area":"lr"},{"id":"2501.13851","title":"Large Vision-Language Models for Knowledge-Grounded Data Annotation of Memes","created":"2025-01-23","cited_by_count":2,"area":"mllm"},{"id":"2502.09073","title":"Enhancing RAG with Active Learning on Conversation Records: Reject Incapables and Answer Capables","created":"2025-02-13","cited_by_count":2,"area":"rag"},{"id":"2503.06778","title":"Large Language Models Are Effective Human Annotation Assistants, But Not Good Independent Annotators","created":"2025-03-09","cited_by_count":2,"area":null},{"id":"2503.09701","title":"Reassessing Active Learning Adoption in Contemporary NLP: A Community Survey","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2505.08905","title":"Grounding Synthetic Data Evaluations of Language Models in Unsupervised Document Corpora","created":"2025-05-13","cited_by_count":2,"area":"synth"},{"id":"2505.13418","title":"Dementia Through Different Eyes: Explainable Modeling of Human and LLM Perceptions for Early Awareness","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2506.10504","title":"Beyond Single-User Dialogue: Assessing Multi-User Dialogue State Tracking Capabilities of Large Language Models","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2509.11687","title":"A Dynamic Knowledge Update-Driven Model with Large Language Models for Fake News Detection","created":"2025-09-15","cited_by_count":2,"area":null},{"id":"2510.04024","title":"Enhancing Fake News Video Detection via LLM-Driven Creative Process Simulation","created":"2025-10-05","cited_by_count":2,"area":null},{"id":"2510.23590","title":"Lightweight Robust Direct Preference Optimization","created":"2025-10-27","cited_by_count":2,"area":"alignment"}],"next_cursor":"100"}