{"total":42,"rows":[{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"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":"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":"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":"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":"2312.02436","title":"MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following","created":"2023-12-05","cited_by_count":30,"area":null},{"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":"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":"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":"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":"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":"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":"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":"2511.07380","title":"Mining Useful General Data for Low-Resource Domain Adaptation","created":"2025-11-10","cited_by_count":4,"area":null},{"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":"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":"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":"2506.02689","title":"MASTER: Enhancing Large Language Model via Multi-Agent Simulated Teaching","created":"2025-06-03","cited_by_count":2,"area":null},{"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":"2509.14738","title":"UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets","created":"2025-09-18","cited_by_count":1,"area":null},{"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},{"id":"2512.14527","title":"Dynamic Learning Rate Scheduling based on Loss Changes Leads to Faster Convergence","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2601.08844","title":"Emissions and Performance Trade-off Between Small and Large Language Models","created":"2025-12-21","cited_by_count":0,"area":null},{"id":"2603.17504","title":"Inducing Epistemological Humility in Large Language Models: A Targeted SFT Approach to Reducing Hallucination","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2608.25005","title":"The Imperfective Paradox Is Not Necessarily in Large Language Models: A Benchmark Failure Before a Model Failure","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}