{"total":77,"rows":[{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344,"area":null},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2310.07820","title":"Large Language Models Are Zero-Shot Time Series Forecasters","created":"2023-10-11","cited_by_count":500,"area":null},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229,"area":null},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202,"area":null},{"id":"2403.18105","title":"Large Language Models for Education: A Survey and Outlook","created":"2024-03-26","cited_by_count":188,"area":null},{"id":"2305.14930","title":"In-Context Impersonation Reveals Large Language Models' Strengths and Biases","created":"2023-05-24","cited_by_count":155,"area":null},{"id":"2308.11730","title":"Knowledge Graph Prompting for Multi-Document Question Answering","created":"2023-08-22","cited_by_count":152,"area":null},{"id":"2307.03381","title":"Teaching Arithmetic to Small Transformers","created":"2023-07-07","cited_by_count":123,"area":null},{"id":"2305.15525","title":"Large Language Models are Few-Shot Health Learners","created":"2023-05-24","cited_by_count":118,"area":null},{"id":"2405.12209","title":"MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark","created":"2024-05-20","cited_by_count":105,"area":null},{"id":"2305.14201","title":"Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks","created":"2023-05-23","cited_by_count":84,"area":null},{"id":"2309.03241","title":"GPT Can Solve Mathematical Problems Without a Calculator","created":"2023-09-06","cited_by_count":68,"area":null},{"id":"2409.01658","title":"From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning","created":"2024-09-03","cited_by_count":54,"area":null},{"id":"2305.06453","title":"Autonomous GIS: the next-generation AI-powered GIS","created":"2023-05-10","cited_by_count":53,"area":null},{"id":"2404.02893","title":"ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline","created":"2024-04-03","cited_by_count":47,"area":null},{"id":"2410.05440","title":"Can LLMs Understand Time Series Anomalies?","created":"2024-10-07","cited_by_count":41,"area":null},{"id":"2310.06116","title":"OptiMUS: Optimization Modeling Using MIP Solvers and large language models","created":"2023-10-09","cited_by_count":39,"area":null},{"id":"2404.16563","title":"Evaluating Large Language Models on Time Series Feature Understanding: A Comprehensive Taxonomy and Benchmark","created":"2024-04-25","cited_by_count":38,"area":null},{"id":"2406.00936","title":"A Survey of Useful LLM Evaluation","created":"2024-06-03","cited_by_count":29,"area":null},{"id":"2310.01386","title":"Who is ChatGPT? Benchmarking LLMs' Psychological Portrayal Using PsychoBench","created":"2023-10-02","cited_by_count":28,"area":null},{"id":"2310.11616","title":"Evidence of interrelated cognitive-like capabilities in large language models: Indications of artificial general intelligence or achievement?","created":"2023-10-17","cited_by_count":27,"area":null},{"id":"2312.07622","title":"Mathematical Language Models: A Survey","created":"2023-12-12","cited_by_count":24,"area":null},{"id":"2410.04691","title":"Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning","created":"2024-10-07","cited_by_count":21,"area":null},{"id":"2411.10478","title":"Large Language Models for Constructing and Optimizing Machine Learning Workflows: A Survey","created":"2024-11-11","cited_by_count":19,"area":null},{"id":"2309.01660","title":"Unveiling Theory of Mind in Large Language Models: A Parallel to Single Neurons in the Human Brain","created":"2023-09-04","cited_by_count":18,"area":null},{"id":"2406.04344","title":"Verbalized Machine Learning: Revisiting Machine Learning with Language Models","created":"2024-06-06","cited_by_count":17,"area":null},{"id":"2410.04368","title":"Algorithmic Capabilities of Random Transformers","created":"2024-10-06","cited_by_count":17,"area":null},{"id":"2311.07387","title":"Assessing Logical Puzzle Solving in Large Language Models: Insights from a Minesweeper Case Study","created":"2023-11-13","cited_by_count":15,"area":null},{"id":"2401.09074","title":"Code Simulation Challenges for Large Language Models","created":"2024-01-17","cited_by_count":15,"area":null},{"id":"2502.19981","title":"The Lookahead Limitation: Why Multi-Operand Addition is Hard for LLMs","created":"2025-02-27","cited_by_count":15,"area":null},{"id":"2501.14457","title":"Understanding and Mitigating Gender Bias in LLMs via Interpretable Neuron Editing","created":"2025-01-24","cited_by_count":14,"area":null},{"id":"2401.08664","title":"Adapting Large Language Models for Education: Foundational Capabilities, Potentials, and Challenges","created":"2023-12-27","cited_by_count":13,"area":null},{"id":"2308.01154","title":"Arithmetic with Language Models: from Memorization to Computation","created":"2023-08-02","cited_by_count":12,"area":null},{"id":"2404.13099","title":"Mathify: Evaluating Large Language Models on Mathematical Problem Solving Tasks","created":"2024-04-19","cited_by_count":12,"area":null},{"id":"2405.19313","title":"Language Models Trained to do Arithmetic Predict Human Risky and Intertemporal Choice","created":"2024-05-29","cited_by_count":12,"area":null},{"id":"2406.14955","title":"ICLEval: Evaluating In-Context Learning Ability of Large Language Models","created":"2024-06-21","cited_by_count":12,"area":null},{"id":"2312.09203","title":"Measurement in the Age of LLMs: An Application to Ideological Scaling","created":"2023-12-14","cited_by_count":11,"area":null},{"id":"2412.15184","title":"Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning","created":"2024-12-19","cited_by_count":11,"area":null},{"id":"2304.14276","title":"AI, write an essay for me: A large-scale comparison of human-written versus ChatGPT-generated essays","created":"2023-04-24","cited_by_count":10,"area":null},{"id":"2403.05845","title":"Reverse That Number! Decoding Order Matters in Arithmetic Learning","created":"2024-03-09","cited_by_count":9,"area":null},{"id":"2501.09349","title":"ChartInsighter: An Approach for Mitigating Hallucination in Time-series Chart Summary Generation with A Benchmark Dataset","created":"2025-01-16","cited_by_count":9,"area":null},{"id":"2311.02945","title":"PhoGPT: Generative Pre-training for Vietnamese","created":"2023-11-06","cited_by_count":8,"area":null},{"id":"2409.17391","title":"Scaling Behavior for Large Language Models regarding Numeral Systems: An Example using Pythia","created":"2024-09-25","cited_by_count":8,"area":null},{"id":"2503.12440","title":"HKCanto-Eval: A Benchmark for Evaluating Cantonese Language Understanding and Cultural Comprehension in LLMs","created":"2025-03-16","cited_by_count":8,"area":null},{"id":"2502.03568","title":"Code Simulation as a Proxy for High-order Tasks in Large Language Models","created":"2025-02-05","cited_by_count":7,"area":null},{"id":"2511.03570","title":"TabGemma: Text-Based Tabular ICL via LLM using Continued Pretraining and Retrieval","created":"2025-11-05","cited_by_count":6,"area":null},{"id":"2311.06720","title":"Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer","created":"2023-11-12","cited_by_count":5,"area":null},{"id":"2401.04218","title":"Distortions in Judged Spatial Relations in Large Language Models","created":"2024-01-08","cited_by_count":5,"area":null},{"id":"2507.17691","title":"CASCADE: LLM-Powered JavaScript Deobfuscator at Google","created":"2025-07-23","cited_by_count":5,"area":null},{"id":"2308.11189","title":"Diversity Measures: Domain-Independent Proxies for Failure in Language Model Queries","created":"2023-08-22","cited_by_count":4,"area":null},{"id":"2309.17339","title":"Scaling Experiments in Self-Supervised Cross-Table Representation Learning","created":"2023-09-29","cited_by_count":4,"area":null},{"id":"2501.15022","title":"Using Large Language Models for education managements in Vietnamese with low resources","created":"2025-01-25","cited_by_count":4,"area":null},{"id":"2507.03682","title":"Towards Machine Theory of Mind with Large Language Model-Augmented Inverse Planning","created":"2025-07-04","cited_by_count":4,"area":null},{"id":"2407.01047","title":"Development of Cognitive Intelligence in Pre-trained Language Models","created":"2024-07-01","cited_by_count":3,"area":null},{"id":"2305.05377","title":"Professional Certification Benchmark Dataset: The First 500 Jobs For Large Language Models","created":"2023-05-07","cited_by_count":2,"area":null},{"id":"2410.10481","title":"Model-based Large Language Model Customization as Service","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2503.11182","title":"Palette of Language Models: A Solver for Controlled Text Generation","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2510.10066","title":"OBsmith: LLM-Powered JavaScript Obfuscator Testing","created":"2025-10-11","cited_by_count":2,"area":null},{"id":"2402.15929","title":"Certifying Knowledge Comprehension in LLMs","created":"2024-02-24","cited_by_count":1,"area":null},{"id":"2403.11473","title":"Word Order's Impacts: Insights from Reordering and Generation Analysis","created":"2024-03-18","cited_by_count":1,"area":null},{"id":"2410.00519","title":"Exploring the Learning Capabilities of Language Models using LEVERWORLDS","created":"2024-10-01","cited_by_count":1,"area":null},{"id":"2501.06964","title":"Enhancing Patient-Centric Communication: Leveraging LLMs to Simulate Patient Perspectives","created":"2025-01-12","cited_by_count":1,"area":null},{"id":"2501.12980","title":"Implicit Causality-biases in humans and LLMs as a tool for benchmarking LLM discourse capabilities","created":"2025-01-22","cited_by_count":1,"area":null},{"id":"2511.08747","title":"Vector Symbolic Algebras for the Abstraction and Reasoning Corpus","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2601.14175","title":"A model of errors in transformers","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2309.15866","title":"ChatGPT & Mechanical Engineering: Examining performance on the FE Mechanical Engineering and Undergraduate Exams","created":"2023-09-26","cited_by_count":0,"area":null},{"id":"2312.10603","title":"Evaluating AI Vocational Skills Through Professional Testing","created":"2023-12-17","cited_by_count":0,"area":null},{"id":"2404.10200","title":"TEL'M: Test and Evaluation of Language Models","created":"2024-04-16","cited_by_count":0,"area":null},{"id":"2405.04170","title":"D-NLP at SemEval-2024 Task 2: Evaluating Clinical Inference Capabilities of Large Language Models","created":"2024-05-07","cited_by_count":0,"area":null},{"id":"2406.15173","title":"\\'Evaluation des capacit\\'es de r\\'eponse de larges mod\\`eles de langage (LLM) pour des questions d'historiens","created":"2024-06-21","cited_by_count":0,"area":null},{"id":"2412.00129","title":"Scaling Particle Collision Data Analysis","created":"2024-11-28","cited_by_count":0,"area":null},{"id":"2504.03713","title":"RLDBF: Enhancing LLMs Via Reinforcement Learning With DataBase FeedBack","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2602.00871","title":"Beyond Output Critique: Self-Correction via Task Distillation","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2602.13262","title":"General learned delegation by clones","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2605.20369","title":"DEL: Digit Entropy Loss for Numerical Learning of Large Language Models","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.03645","title":"The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models","created":"2026-05-29","cited_by_count":0,"area":null}],"next_cursor":null}