{"total":82,"rows":[{"id":"2311.16079","title":"MEDITRON-70B: Scaling Medical Pretraining for Large Language Models","created":"2023-11-27","cited_by_count":274,"area":null},{"id":"2403.03883","title":"SaulLM-7B: A pioneering Large Language Model for Law","created":"2024-03-06","cited_by_count":142,"area":null},{"id":"2404.07965","title":"Rho-1: Not All Tokens Are What You Need","created":"2024-04-11","cited_by_count":133,"area":null},{"id":"2402.12348","title":"GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations","created":"2024-02-19","cited_by_count":120,"area":"lr"},{"id":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100,"area":"lr"},{"id":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93,"area":null},{"id":"2502.10341","title":"Organize the Web: Constructing Domains Enhances Pre-Training Data Curation","created":"2025-02-14","cited_by_count":76,"area":null},{"id":"2406.11050","title":"A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners","created":"2024-06-16","cited_by_count":73,"area":"lr"},{"id":"2505.04481","title":"CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generation","created":"2025-05-07","cited_by_count":67,"area":null},{"id":"2411.00622","title":"Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement","created":"2024-11-01","cited_by_count":61,"area":"agents"},{"id":"2402.08785","title":"InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment","created":"2024-02-13","cited_by_count":56,"area":"lr"},{"id":"2408.10914","title":"To Code, or Not To Code? Exploring Impact of Code in Pre-training","created":"2024-08-20","cited_by_count":47,"area":null},{"id":"2410.11820","title":"Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws","created":"2024-10-15","cited_by_count":47,"area":null},{"id":"2502.19411","title":"Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs","created":"2025-02-26","cited_by_count":47,"area":"lr"},{"id":"2505.11049","title":"GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning","created":"2025-05-16","cited_by_count":42,"area":"lr"},{"id":"2407.08699","title":"Mitigating Catastrophic Forgetting in Language Transfer via Model Merging","created":"2024-07-11","cited_by_count":36,"area":null},{"id":"2408.08313","title":"Can Large Language Models Understand Symbolic Graphics Programs?","created":"2024-08-15","cited_by_count":35,"area":null},{"id":"2405.20535","title":"Unveiling the Impact of Coding Data Instruction Fine-Tuning on Large Language Models Reasoning","created":"2024-05-30","cited_by_count":31,"area":"lr"},{"id":"2405.21068","title":"Code Pretraining Improves Entity Tracking Abilities of Language Models","created":"2024-05-31","cited_by_count":31,"area":null},{"id":"2410.16232","title":"Sketch2Code: Evaluating Vision-Language Models for Interactive Web Design Prototyping","created":"2024-10-21","cited_by_count":29,"area":"mllm"},{"id":"2411.12498","title":"Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus","created":"2024-11-19","cited_by_count":29,"area":"lr"},{"id":"2409.04556","title":"How Does Code Pretraining Affect Language Model Task Performance?","created":"2024-09-06","cited_by_count":28,"area":null},{"id":"2503.23803","title":"Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute","created":"2025-03-31","cited_by_count":26,"area":"lr"},{"id":"2510.13554","title":"Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization","created":"2025-10-15","cited_by_count":25,"area":"lr"},{"id":"2505.14667","title":"SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment","created":"2025-05-20","cited_by_count":24,"area":"lr"},{"id":"2504.12459","title":"On Linear Representations and Pretraining Data Frequency in Language Models","created":"2025-04-16","cited_by_count":23,"area":null},{"id":"2509.26625","title":"Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training","created":"2025-09-30","cited_by_count":23,"area":null},{"id":"2404.09554","title":"Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda","created":"2024-04-15","cited_by_count":22,"area":null},{"id":"2506.01732","title":"Common Corpus: The Largest Collection of Ethical Data for LLM Pre-Training","created":"2025-06-02","cited_by_count":20,"area":null},{"id":"2410.01353","title":"Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?","created":"2024-10-02","cited_by_count":18,"area":null},{"id":"2410.13394","title":"Cross-Lingual Auto Evaluation for Assessing Multilingual LLMs","created":"2024-10-17","cited_by_count":18,"area":null},{"id":"2509.24365","title":"Uni-X: Mitigating Modality Conflict with a Two-End-Separated Architecture for Unified Multimodal Models","created":"2025-09-29","cited_by_count":18,"area":null},{"id":"2409.17892","title":"EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models","created":"2024-09-26","cited_by_count":16,"area":null},{"id":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"id":"2503.09202","title":"Token Weighting for Long-Range Language Modeling","created":"2025-03-12","cited_by_count":14,"area":null},{"id":"2505.24844","title":"Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning","created":"2025-05-30","cited_by_count":14,"area":null},{"id":"2407.16607","title":"Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?","created":"2024-07-23","cited_by_count":13,"area":null},{"id":"2503.03862","title":"Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions","created":"2025-03-05","cited_by_count":12,"area":null},{"id":"2506.10766","title":"One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers","created":"2025-06-12","cited_by_count":12,"area":null},{"id":"2603.20432","title":"Coding Agents are Effective Long-Context Processors","created":"2026-03-20","cited_by_count":12,"area":"agents"},{"id":"2408.09070","title":"CodeTaxo: Enhancing Taxonomy Expansion with Limited Examples via Code Language Prompts","created":"2024-08-17","cited_by_count":10,"area":null},{"id":"2410.02229","title":"CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning","created":"2024-10-03","cited_by_count":10,"area":"lr"},{"id":"2411.13941","title":"LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues","created":"2024-11-21","cited_by_count":10,"area":null},{"id":"2504.04152","title":"Rethinking Multilingual Continual Pretraining: Data Mixing for Adapting LLMs Across Languages and Resources","created":"2025-04-05","cited_by_count":10,"area":"lr"},{"id":"2403.15230","title":"An Exploratory Investigation into Code License Infringements in Large Language Model Training Datasets","created":"2024-03-22","cited_by_count":9,"area":null},{"id":"2505.12534","title":"ChemPile: A 250GB Diverse and Curated Dataset for Chemical Foundation Models","created":"2025-05-18","cited_by_count":9,"area":null},{"id":"2505.15214","title":"R-TOFU: Unlearning in Large Reasoning Models","created":"2025-05-21","cited_by_count":9,"area":"lr"},{"id":"2604.03071","title":"Automatic Textbook Formalization","created":"2026-04-03","cited_by_count":8,"area":null},{"id":"2406.06590","title":"Are LLMs classical or nonmonotonic reasoners? Lessons from generics","created":"2024-06-05","cited_by_count":7,"area":"lr"},{"id":"2407.00416","title":"Too Late to Train, Too Early To Use? A Study on Necessity and Viability of Low-Resource Bengali LLMs","created":"2024-06-29","cited_by_count":7,"area":null},{"id":"2503.10968","title":"Combinatorial Optimization for All: Using LLMs to Aid Non-Experts in Improving Optimization Algorithms","created":"2025-03-14","cited_by_count":7,"area":null},{"id":"2505.19756","title":"Efficient Reasoning via Chain of Unconscious Thought","created":"2025-05-26","cited_by_count":7,"area":"lr"},{"id":"2506.14276","title":"Don't throw the baby out with the bathwater: How and why deep learning for ARC","created":"2025-06-17","cited_by_count":7,"area":null},{"id":"2509.16596","title":"Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels","created":"2025-09-20","cited_by_count":7,"area":null},{"id":"2408.03506","title":"1.5-Pints Technical Report: Pretraining in Days, Not Months -- Your Language Model Thrives on Quality Data","created":"2024-08-07","cited_by_count":6,"area":null},{"id":"2408.13863","title":"CodeGraph: Enhancing Graph Reasoning of LLMs with Code","created":"2024-08-25","cited_by_count":6,"area":"lr"},{"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":"2506.07452","title":"When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment","created":"2025-06-09","cited_by_count":6,"area":"safety"},{"id":"2510.01232","title":"Benchmark Profiling: Mechanistic Diagnosis of LLM Benchmarks","created":"2025-09-23","cited_by_count":6,"area":null},{"id":"2409.02326","title":"Arctic-SnowCoder: Demystifying High-Quality Data in Code Pretraining","created":"2024-09-03","cited_by_count":5,"area":null},{"id":"2411.04156","title":"Crystal: Illuminating LLM Abilities on Language and Code","created":"2024-11-06","cited_by_count":5,"area":null},{"id":"2502.04643","title":"Confidence Elicitation: A New Attack Vector for Large Language Models","created":"2025-02-07","cited_by_count":5,"area":null},{"id":"2508.04865","title":"Agnostics: Learning to Code in Any Programming Language via Reinforcement with a Universal Learning Environment","created":"2025-08-06","cited_by_count":5,"area":null},{"id":"2509.21499","title":"On Code-Induced Reasoning in LLMs","created":"2025-09-25","cited_by_count":5,"area":"lr"},{"id":"2602.17684","title":"CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models","created":"2026-02-04","cited_by_count":5,"area":"alignment"},{"id":"2404.07549","title":"Comments as Natural Logic Pivots: Improve Code Generation via Comment Perspective","created":"2024-04-11","cited_by_count":3,"area":"lr"},{"id":"2412.11699","title":"CoinMath: Harnessing the Power of Coding Instruction for Math LLMs","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2503.05397","title":"Multi Agent based Medical Assistant for Edge Devices","created":"2025-03-07","cited_by_count":2,"area":null},{"id":"2607.11052","title":"Domain-Aware Scaling Laws Uncover Data Synergy","created":"2026-07-13","cited_by_count":2,"area":null},{"id":"2405.19773","title":"VQA Training Sets are Self-play Environments for Generating Few-shot Pools","created":"2024-05-30","cited_by_count":1,"area":"synth"},{"id":"2407.13419","title":"From Words to Worlds: Compositionality for Cognitive Architectures","created":"2024-07-18","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":"2510.16022","title":"Breaking Memorization Barriers in LLM Code Fine-Tuning via Information Bottleneck for Improved Generalization","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2601.01244","title":"Racka: Efficient Hungarian LLM Adaptation on Academic Infrastructure","created":"2026-01-03","cited_by_count":1,"area":null},{"id":"2601.21894","title":"Not All Code Is Equal: A Data-Centric Study of Code Complexity and LLM Reasoning","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2602.03542","title":"Can Large Language Models Generalize Procedures Across Representations?","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2604.00715","title":"To Memorize or to Retrieve: Scaling the Interaction Between Pretraining and Retrieval","created":"2026-04-01","cited_by_count":1,"area":"rag"},{"id":"2604.00920","title":"GPT-NL Public Corpus: A Permissively Licensed, Dutch-First Dataset for LLM Pre-training","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2605.19762","title":"What Really Improves Mathematical Reasoning: Structured Reasoning Signals Beyond Pure Code","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2603.15953","title":"A Family of LLMs Liberated from Static Vocabularies","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2609.33845","title":"How code helps different tasks? A decompositional lens on LLM post-training","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.38879","title":"Does Learning Protein Folding Generalize to Broader Reasoning?","created":"2026-09-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}