{"total":108,"rows":[{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212,"area":"lr"},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2310.08491","title":"Prometheus: Inducing Fine-grained Evaluation Capability in Language Models","created":"2023-10-12","cited_by_count":575,"area":"alignment"},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201,"area":"alignment"},{"id":"2309.15402","title":"Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future","created":"2023-09-27","cited_by_count":184,"area":"lr"},{"id":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177,"area":null},{"id":"2401.06591","title":"Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation","created":"2024-01-12","cited_by_count":125,"area":"mllm"},{"id":"2410.23123","title":"On Memorization of Large Language Models in Logical Reasoning","created":"2024-10-30","cited_by_count":117,"area":"lr"},{"id":"2311.07914","title":"Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey","created":"2023-11-14","cited_by_count":92,"area":null},{"id":"2402.13963","title":"Towards Building Multilingual Language Model for Medicine","created":"2024-02-21","cited_by_count":92,"area":null},{"id":"2502.03275","title":"Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning","created":"2025-02-05","cited_by_count":91,"area":"lr"},{"id":"2403.20046","title":"Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning","created":"2024-03-29","cited_by_count":69,"area":"lr"},{"id":"2402.05808","title":"Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning","created":"2024-02-08","cited_by_count":65,"area":"lr"},{"id":"2507.08794","title":"One Token to Fool LLM-as-a-Judge","created":"2025-07-11","cited_by_count":60,"area":"alignment"},{"id":"2503.12799","title":"Grounded Chain-of-Thought for Multimodal Large Language Models","created":"2025-03-17","cited_by_count":59,"area":"lr"},{"id":"2310.05707","title":"Guiding Language Model Reasoning with Planning Tokens","created":"2023-10-09","cited_by_count":58,"area":"lr"},{"id":"2311.05661","title":"Prompt Engineering a Prompt Engineer","created":"2023-11-09","cited_by_count":53,"area":null},{"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":"2404.04735","title":"MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems","created":"2024-04-06","cited_by_count":41,"area":"lr"},{"id":"2502.17521","title":"Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation","created":"2025-02-23","cited_by_count":38,"area":null},{"id":"2409.15277","title":"A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor?","created":"2024-09-23","cited_by_count":33,"area":null},{"id":"2412.03679","title":"Evaluating Language Models as Synthetic Data Generators","created":"2024-12-04","cited_by_count":33,"area":"synth"},{"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":"2402.15527","title":"PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain","created":"2024-02-21","cited_by_count":29,"area":"mllm"},{"id":"2410.05459","title":"From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency","created":"2024-10-07","cited_by_count":29,"area":"lr"},{"id":"2407.19200","title":"On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs","created":"2024-07-27","cited_by_count":25,"area":"mechinterp"},{"id":"2410.08085","title":"Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study Over Open-ended Question Answering","created":"2024-10-10","cited_by_count":24,"area":"lr"},{"id":"2506.00070","title":"Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics","created":"2025-05-29","cited_by_count":21,"area":"lr"},{"id":"2403.07794","title":"Fine-tuning Large Language Models with Sequential Instructions","created":"2024-03-12","cited_by_count":20,"area":null},{"id":"2402.10891","title":"Instruction Diversity Drives Generalization To Unseen Tasks","created":"2024-02-16","cited_by_count":16,"area":null},{"id":"2503.18172","title":"Unmasking Deceptive Visuals: Benchmarking Multimodal Large Language Models on Misleading Chart Question Answering","created":"2025-03-23","cited_by_count":16,"area":"mllm"},{"id":"2405.04086","title":"Optimizing Language Model's Reasoning Abilities with Weak Supervision","created":"2024-05-07","cited_by_count":15,"area":"lr"},{"id":"2404.09296","title":"Cross-Data Knowledge Graph Construction for LLM-enabled Educational Question-Answering System: A Case Study at HCMUT","created":"2024-04-14","cited_by_count":14,"area":null},{"id":"2409.01893","title":"What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practices","created":"2024-09-03","cited_by_count":14,"area":"lr"},{"id":"2508.09804","title":"BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning","created":"2025-08-13","cited_by_count":13,"area":"lr"},{"id":"2306.17820","title":"Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language Models","created":"2023-06-30","cited_by_count":11,"area":"lr"},{"id":"2511.00330","title":"Sherlock: Reliable and Efficient Agentic Workflow Execution","created":"2025-11-01","cited_by_count":11,"area":"lr"},{"id":"2502.04667","title":"Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning","created":"2025-02-07","cited_by_count":10,"area":"lr"},{"id":"2404.18564","title":"Injecting Salesperson's Dialogue Strategies in Large Language Models with Chain-of-Thought Reasoning","created":"2024-04-29","cited_by_count":9,"area":"lr"},{"id":"2403.14312","title":"ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting","created":"2024-03-21","cited_by_count":8,"area":"lr"},{"id":"2405.20192","title":"TAIA: Large Language Models are Out-of-Distribution Data Learners","created":"2024-05-30","cited_by_count":8,"area":null},{"id":"2411.15927","title":"Generative Prompt Internalization","created":"2024-11-24","cited_by_count":8,"area":null},{"id":"2406.09103","title":"Chain-of-Though (CoT) prompting strategies for medical error detection and correction","created":"2024-06-13","cited_by_count":7,"area":null},{"id":"2406.15275","title":"How language models extrapolate outside the training data: A case study in Textualized Gridworld","created":"2024-06-21","cited_by_count":7,"area":null},{"id":"2411.10129","title":"Prompting and Fine-tuning Large Language Models for Automated Code Review Comment Generation","created":"2024-11-15","cited_by_count":7,"area":null},{"id":"2505.17266","title":"Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning","created":"2025-05-22","cited_by_count":7,"area":"lr"},{"id":"2506.22920","title":"Improving Rationality in the Reasoning Process of Language Models through Self-playing Game","created":"2025-06-28","cited_by_count":7,"area":"lr"},{"id":"2404.16418","title":"Instruction Matters: A Simple yet Effective Task Selection for Optimized Instruction Tuning of Specific Tasks","created":"2024-04-25","cited_by_count":6,"area":null},{"id":"2412.10654","title":"Thinking with Knowledge Graphs: Enhancing LLM Reasoning Through Structured Data","created":"2024-12-14","cited_by_count":6,"area":"lr"},{"id":"2503.15235","title":"Exploring Large Language Models for Word Games:Who is the Spy?","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2506.23908","title":"Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence","created":"2025-06-30","cited_by_count":6,"area":"lr"},{"id":"2403.11456","title":"HateCOT: An Explanation-Enhanced Dataset for Generalizable Offensive Speech Detection via Large Language Models","created":"2024-03-18","cited_by_count":5,"area":null},{"id":"2408.14504","title":"Is Functional Correctness Enough to Evaluate Code Language Models? Exploring Diversity of Generated Codes","created":"2024-08-24","cited_by_count":5,"area":null},{"id":"2409.08098","title":"The CLC-UKET Dataset: Benchmarking Case Outcome Prediction for the UK Employment Tribunal","created":"2024-09-12","cited_by_count":5,"area":null},{"id":"2502.18273","title":"Beyond In-Distribution Success: Scaling Curves of CoT Granularity for Language Model Generalization","created":"2025-02-25","cited_by_count":5,"area":null},{"id":"2404.07017","title":"Improving Language Model Reasoning with Self-motivated Learning","created":"2024-04-10","cited_by_count":4,"area":"lr"},{"id":"2409.06241","title":"DiPT: Enhancing LLM reasoning through diversified perspective-taking","created":"2024-09-10","cited_by_count":4,"area":"lr"},{"id":"2412.21006","title":"Verbosity-Aware Rationale Reduction: Effective Reduction of Redundant Rationale via Principled Criteria","created":"2024-12-30","cited_by_count":4,"area":null},{"id":"2502.15132","title":"CoT-ICL Lab: A Synthetic Framework for Studying Chain-of-Thought Learning from In-Context Demonstrations","created":"2025-02-21","cited_by_count":4,"area":"lr"},{"id":"2511.07380","title":"Mining Useful General Data for Low-Resource Domain Adaptation","created":"2025-11-10","cited_by_count":4,"area":null},{"id":"2512.21017","title":"Rethinking Supervised Fine-Tuning: Emphasizing Key Answer Tokens for Improved LLM Accuracy","created":"2025-12-24","cited_by_count":4,"area":"lr"},{"id":"2401.07510","title":"Developing ChatGPT for Biology and Medicine: A Complete Review of Biomedical Question Answering","created":"2024-01-15","cited_by_count":3,"area":null},{"id":"2506.02519","title":"Learning Together to Perform Better: Teaching Small-Scale LLMs to Collaborate via Preferential Rationale Tuning","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2507.13332","title":"The Imitation Game: Turing Machine Imitator is Length Generalizable Reasoner","created":"2025-07-17","cited_by_count":3,"area":"lr"},{"id":"2510.07000","title":"Pragyaan: Designing and Curating High-Quality Cultural Post-Training Datasets for Indian Languages","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2510.18470","title":"CircuitSeer: Mining High-Quality Data by Probing Mathematical Reasoning Circuits in LLMs","created":"2025-10-21","cited_by_count":3,"area":"lr"},{"id":"2603.21341","title":"RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models","created":"2026-03-22","cited_by_count":3,"area":"lr"},{"id":"2401.04319","title":"Know Your Needs Better: Towards Structured Understanding of Marketer Demands with Analogical Reasoning Augmented LLMs","created":"2024-01-09","cited_by_count":2,"area":"lr"},{"id":"2405.19763","title":"Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding","created":"2024-05-30","cited_by_count":2,"area":"alignment"},{"id":"2408.05566","title":"Document-Level Event Extraction with Definition-Driven ICL","created":"2024-08-10","cited_by_count":2,"area":null},{"id":"2501.00106","title":"LicenseGPT: A Fine-tuned Foundation Model for Publicly Available Dataset License Compliance","created":"2024-12-30","cited_by_count":2,"area":null},{"id":"2504.09488","title":"Kongzi: A Historical Large Language Model with Fact Enhancement","created":"2025-04-13","cited_by_count":2,"area":null},{"id":"2504.18942","title":"LawFlow: Collecting and Simulating Lawyers' Thought Processes on Business Formation Case Studies","created":"2025-04-26","cited_by_count":2,"area":"lr"},{"id":"2506.02689","title":"MASTER: Enhancing Large Language Model via Multi-Agent Simulated Teaching","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2509.11071","title":"The System Description of CPS Team for Track on Driving with Language of CVPR 2024 Autonomous Grand Challenge","created":"2025-09-14","cited_by_count":2,"area":"mllm"},{"id":"2403.05680","title":"How Well Do Multi-modal LLMs Interpret CT Scans? An Auto-Evaluation Framework for Analyses","created":"2024-03-08","cited_by_count":1,"area":null},{"id":"2404.13033","title":"Sample Design Engineering: An Empirical Study of What Makes Good Downstream Fine-Tuning Samples for LLMs","created":"2024-04-19","cited_by_count":1,"area":null},{"id":"2503.02463","title":"It Helps to Take a Second Opinion: Teaching Smaller LLMs to Deliberate Mutually via Selective Rationale Optimisation","created":"2025-03-04","cited_by_count":1,"area":null},{"id":"2503.13980","title":"Empowering LLMs in Decision Games through Algorithmic Data Synthesis","created":"2025-03-18","cited_by_count":1,"area":"synth"},{"id":"2503.17136","title":"CoKe: Customizable Fine-Grained Story Evaluation via Chain-of-Keyword Rationalization","created":"2025-03-21","cited_by_count":1,"area":"lr"},{"id":"2507.18857","title":"PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning","created":"2025-07-25","cited_by_count":1,"area":"lr"},{"id":"2508.10020","title":"FedCoT: Communication-Efficient Federated Reasoning Enhancement for Large Language Models","created":"2025-08-07","cited_by_count":1,"area":"lr"},{"id":"2509.14738","title":"UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2510.16095","title":"Reliability of Large Language Model Generated Clinical Reasoning in Assisted Reproductive Technology: Blinded Comparative Evaluation Study","created":"2025-10-17","cited_by_count":1,"area":"lr"},{"id":"2512.24555","title":"From Perception to Punchline: Empowering VLM with the Art of In-the-wild Meme","created":"2025-12-31","cited_by_count":1,"area":"lr"},{"id":"2601.04672","title":"Agri-R1: Agricultural Reasoning for Disease Diagnosis via Automated-Synthesis and Reinforcement Learning","created":"2026-01-08","cited_by_count":1,"area":"lr"},{"id":"2602.21053","title":"OCR-Agent: Agentic OCR with Capability and Memory Reflection","created":"2026-02-24","cited_by_count":1,"area":"mllm"},{"id":"2604.24218","title":"RefEvo: Agentic Design with Co-Evolutionary Verification for Agile Reference Model Generation","created":"2026-04-27","cited_by_count":1,"area":"agents"},{"id":"2605.03644","title":"AdapShot: Adaptive Many-Shot In-Context Learning with Semantic-Aware KV Cache Reuse","created":"2026-05-05","cited_by_count":1,"area":"lr"},{"id":"2605.29068","title":"Robust and Efficient Guardrails with Latent Reasoning","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2606.07603","title":"MetaEvo: A Meta-Optimization Framework for Experience-Driven Agent Evolution","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2607.27506","title":"Models for minimalist RAG: B1ade 335M Embedding and 1B Parameter Small Language Models","created":"2026-07-29","cited_by_count":1,"area":"rag"},{"id":"2405.01591","title":"Simplifying Multimodality: Unimodal Approach to Multimodal Challenges in Radiology with General-Domain Large Language Model","created":"2024-04-29","cited_by_count":0,"area":"mllm"},{"id":"2505.23323","title":"Neither Stochastic Parroting nor AGI: LLMs Solve Tasks through Context-Directed Extrapolation from Training Data Priors","created":"2025-05-29","cited_by_count":0,"area":"lr"},{"id":"2506.00527","title":"Retrieval-Augmented Generation Systems for Intellectual Property via Synthetic Multi-Angle Fine-tuning","created":"2025-05-31","cited_by_count":0,"area":"rag"},{"id":"2508.12387","title":"ReaLM: Reflection-Enhanced Autonomous Reasoning with Small Language Models","created":"2025-08-17","cited_by_count":0,"area":"lr"},{"id":"2508.19359","title":"Reflective Agreement: Combining Self-Mixture of Agents with a Sequence Tagger for Robust Event Extraction","created":"2025-08-26","cited_by_count":0,"area":"agents"},{"id":"2509.15174","title":"SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2510.02027","title":"Zero-shot reasoning for simulating scholarly peer-review","created":"2025-10-02","cited_by_count":0,"area":null}],"next_cursor":"100"}