{"total":25,"rows":[{"id":"2512.16676","title":"DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI","created":"2025-12-18","cited_by_count":23,"area":null},{"id":"2601.09195","title":"ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection","created":"2026-01-14","cited_by_count":18,"area":null},{"id":"2512.17843","title":"ShareChat: A Dataset of Chatbot Conversations in the Wild","created":"2025-12-19","cited_by_count":15,"area":null},{"id":"2509.02521","title":"FLM-Audio: Natural Monologues Improves Native Full-Duplex Chatbots via Dual Training","created":"2025-09-02","cited_by_count":11,"area":null},{"id":"2508.20697","title":"Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning","created":"2025-08-28","cited_by_count":8,"area":null},{"id":"2507.10605","title":"RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services","created":"2025-07-13","cited_by_count":6,"area":null},{"id":"2509.05276","title":"SpikingBrain: Spiking Brain-inspired Large Models","created":"2025-09-05","cited_by_count":5,"area":null},{"id":"2509.07370","title":"PersonaFuse: A Personality Activation-Driven Framework for Enhancing Human-LLM Interactions","created":"2025-09-09","cited_by_count":5,"area":null},{"id":"2512.23422","title":"Entropy-Guided Token Dropout: Training Autoregressive Language Models with Limited Domain Data","created":"2025-12-29","cited_by_count":5,"area":null},{"id":"2506.13274","title":"AdaLRS: Loss-Guided Adaptive Learning Rate Search for Efficient Foundation Model Pretraining","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2511.17561","title":"LexInstructEval: Lexical Instruction Following Evaluation for Large Language Models","created":"2025-11-13","cited_by_count":2,"area":null},{"id":"2605.04062","title":"EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation","created":"2026-04-10","cited_by_count":2,"area":null},{"id":"2605.09635","title":"K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs","created":"2026-05-10","cited_by_count":2,"area":null},{"id":"2601.14051","title":"Kakugo: Distillation of Low-Resource Languages into Small Language Models","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2603.07886","title":"CCR-Bench: A Comprehensive Benchmark for Evaluating LLMs on Complex Constraints, Control Flows, and Real-World Cases","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2603.17823","title":"Discovering Decoupled Functional Modules in Large Language Models","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2605.06765","title":"VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2607.20465","title":"DataPrep-Bench: Benchmarking LLMs as Training Data Preparators","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2601.13995","title":"From Tags to Trees: Structuring Fine-Grained Knowledge for Controllable Data Selection in LLM Instruction Tuning","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2601.21503","title":"MAR: Efficient Large Language Models via Module-aware Architecture Refinement","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2603.18593","title":"Language Model Maps for Prompt-Response Distributions via Log-Likelihood Vectors","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2603.21438","title":"PROMPT2BOX:Improving LLM Weakness Discovery and Specificity Estimation by Uncovering Entailment Structure among Prompts","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2607.02118","title":"Enhancing Fitness Intelligence through Domain-Specific LLM Post-Training","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.04619","title":"CARD: Cross-component Audio Representation Distillation for Encoder-Free Audio Captioning","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2610.02856","title":"Adaptive Mutual Distillation for Balanced Multi-Task Post-Training of Large Language Models","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}