{"total":60,"rows":[{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2506.10943","title":"Self-Adapting Language Models","created":"2025-06-12","cited_by_count":84,"area":null},{"id":"2410.15226","title":"On the Diversity of Synthetic Data and its Impact on Training Large Language Models","created":"2024-10-19","cited_by_count":59,"area":"synth"},{"id":"2505.08054","title":"FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning","created":"2025-05-12","cited_by_count":58,"area":"lr"},{"id":"2505.10557","title":"MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning","created":"2025-05-15","cited_by_count":45,"area":"lr"},{"id":"2412.13337","title":"Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs","created":"2024-12-17","cited_by_count":40,"area":null},{"id":"2505.00661","title":"On the generalization of language models from in-context learning and finetuning: a controlled study","created":"2025-05-01","cited_by_count":40,"area":"lr"},{"id":"2410.08196","title":"MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code","created":"2024-10-10","cited_by_count":39,"area":"lr"},{"id":"2504.21039","title":"Llama-3.1-FoundationAI-SecurityLLM-Base-8B Technical Report","created":"2025-04-28","cited_by_count":31,"area":null},{"id":"2506.04689","title":"Recycling the Web: A Method to Enhance Pre-training Data Quality and Quantity for Language Models","created":"2025-06-05","cited_by_count":31,"area":null},{"id":"2504.15266","title":"Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction","created":"2025-04-21","cited_by_count":29,"area":null},{"id":"2510.01631","title":"Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls","created":"2025-10-02","cited_by_count":26,"area":"synth"},{"id":"2503.11751","title":"reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs","created":"2025-03-14","cited_by_count":25,"area":"alignment"},{"id":"2503.08727","title":"Training Plug-n-Play Knowledge Modules with Deep Context Distillation","created":"2025-03-11","cited_by_count":24,"area":null},{"id":"2502.14709","title":"Group-Level Data Selection for Efficient Pretraining","created":"2025-02-20","cited_by_count":13,"area":null},{"id":"2504.12523","title":"Memorization vs. Reasoning: Updating LLMs with New Knowledge","created":"2025-04-16","cited_by_count":13,"area":"lr"},{"id":"2508.09494","title":"Learning Facts at Scale with Active Reading","created":"2025-08-13","cited_by_count":13,"area":null},{"id":"2510.14865","title":"Midtraining Bridges Pretraining and Posttraining Distributions","created":"2025-10-16","cited_by_count":12,"area":null},{"id":"2603.01097","title":"Understanding LoRA as Knowledge Memory: An Empirical Analysis","created":"2026-03-01","cited_by_count":12,"area":null},{"id":"2504.14557","title":"Enhancing LLM-based Quantum Code Generation with Multi-Agent Optimization and Quantum Error Correction","created":"2025-04-20","cited_by_count":11,"area":"agents"},{"id":"2505.00263","title":"EnronQA: Towards Personalized RAG over Private Documents","created":"2025-05-01","cited_by_count":9,"area":"rag"},{"id":"2411.07175","title":"Continual Memorization of Factoids in Language Models","created":"2024-11-11","cited_by_count":8,"area":null},{"id":"2605.15188","title":"FutureSim: Replaying World Events to Evaluate Adaptive Agents","created":"2026-05-14","cited_by_count":7,"area":null},{"id":"2509.08653","title":"Generative Data Refinement: Just Ask for Better Data","created":"2025-09-10","cited_by_count":6,"area":null},{"id":"2509.15248","title":"Synthetic bootstrapped pretraining","created":"2025-09-17","cited_by_count":6,"area":"synth"},{"id":"2512.00884","title":"Towards Active Synthetic Data Generation for Finetuning Language Models","created":"2025-11-30","cited_by_count":6,"area":"synth"},{"id":"2604.13977","title":"How Can We Synthesize High-Quality Pretraining Data? A Systematic Study of Prompt Design, Generator Model, and Source Data","created":"2026-04-15","cited_by_count":6,"area":null},{"id":"2505.19145","title":"Do Large Language Models (Really) Need Statistical Foundations?","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2510.10071","title":"ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled Tuning","created":"2025-10-11","cited_by_count":5,"area":null},{"id":"2505.00979","title":"Synthesize-on-Graph: Knowledgeable Synthetic Data Generation for Continue Pre-training of Large Language Models","created":"2025-05-02","cited_by_count":4,"area":"synth"},{"id":"2510.16096","title":"Facts in Stats: Impacts of Pretraining Diversity on Language Model Generalization","created":"2025-10-17","cited_by_count":3,"area":null},{"id":"2602.02366","title":"ReasonCACHE: Teaching LLMs To Reason Without Weight Updates","created":"2026-02-02","cited_by_count":3,"area":"lr"},{"id":"2506.17585","title":"Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2508.06178","title":"Comparing Knowledge Injection Methods for LLMs in a Low-Resource Regime","created":"2025-08-08","cited_by_count":2,"area":null},{"id":"2510.26336","title":"From Amateur to Master: Infusing Knowledge into LLMs via Automated Curriculum Learning","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2604.08423","title":"Synthetic Data for any Differentiable Target","created":"2026-04-09","cited_by_count":2,"area":"lr"},{"id":"2509.21993","title":"Bilinear representation mitigates reversal curse and enables consistent model editing","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2510.18817","title":"Fine-Tuned Thoughts: Leveraging Chain-of-Thought Reasoning for Industrial Asset Health Monitoring","created":"2025-10-21","cited_by_count":1,"area":"lr"},{"id":"2511.03563","title":"ASVRI-Legal: Fine-Tuning LLMs with Retrieval Augmented Generation for Enhanced Legal Regulation","created":"2025-11-05","cited_by_count":1,"area":"rag"},{"id":"2607.24717","title":"DataOrchestra: Learning to Orchestrate Per-Example Curation of Pretraining Data","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2609.30063","title":"Self-Play Pretraining with Zero Data","created":"2026-09-24","cited_by_count":1,"area":"synth"},{"id":"2505.22633","title":"Spatial Knowledge Graph-Guided Multimodal Synthesis","created":"2025-05-28","cited_by_count":0,"area":"mllm"},{"id":"2510.11842","title":"Balancing Synthetic Data and Replay for Enhancing Task-Specific Capabilities","created":"2025-10-13","cited_by_count":0,"area":"synth"},{"id":"2510.16609","title":"Prior Knowledge Makes It Possible: From Sublinear Graph Algorithms to LLM Test-Time Methods","created":"2025-10-18","cited_by_count":0,"area":"rag"},{"id":"2601.22146","title":"FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale","created":"2026-01-29","cited_by_count":0,"area":"synth"},{"id":"2602.18137","title":"Agentic Adversarial QA for Improving Domain-Specific LLMs","created":"2026-02-20","cited_by_count":0,"area":"agents"},{"id":"2603.22213","title":"SPA: A Simple but Tough-to-Beat Baseline for Knowledge Injection","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.01430","title":"Improving Latent Generalization Using Test-time Compute","created":"2026-04-01","cited_by_count":0,"area":"lr"},{"id":"2606.01849","title":"ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.32002","title":"Self-Study Reconsidered: The Hidden Fragility of Learning from Self-Generated QA","created":"2026-06-30","cited_by_count":0,"area":"synth"},{"id":"2608.24268","title":"ROBE: Reversed-Order-Biased-Experts for Extracting Extreme Long-tail Events from Historical Texts","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.25826","title":"Unfolding Scientific Papers into Multi-Turn Generation Trajectories for Continued Pre-Training","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.00082","title":"KItCAT: Knowledge Injection via Input Corruption for Auto-regressive Training","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.16532","title":"Style-Debiased DPO: Updating LLM Knowledge with Factuality-Aware Synthetic Preference Data","created":"2026-09-15","cited_by_count":0,"area":"alignment"},{"id":"2609.37891","title":"It's All Training: A Fully Synthetic Single-Stage Recipe for LLMs","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39702","title":"A helps B while B hurts A: directed transfer in instruction-tuning mixture","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.03251","title":"Learning a Fact Is Not Learning How to Retrieve It","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.08093","title":"SAGE: Semantic Anchor-Guided Evolution for Grounded Medical QA Data Synthesis","created":"2026-10-06","cited_by_count":0,"area":"synth"},{"id":"2610.13835","title":"Specialists Learn Faster: Knowledge Organization in Pre-training Shapes Knowledge Update Efficiency","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.20086","title":"AFCS: Atomic-Fact-Conditioned Synthesis for Factual Knowledge Pretraining","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}