{"total":21,"rows":[{"id":"2502.02421","title":"Activation-Informed Merging of Large Language Models","created":"2025-02-04","cited_by_count":30,"area":null},{"id":"2509.20758","title":"SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs","created":"2025-09-25","cited_by_count":24,"area":null},{"id":"2604.13627","title":"(How) Learning Rates Regulate Catastrophic Overtraining","created":"2026-04-15","cited_by_count":6,"area":null},{"id":"2503.23175","title":"Large Language Models Are Unreliable for Cyber Threat Intelligence","created":"2025-03-29","cited_by_count":5,"area":null},{"id":"2601.13240","title":"KOCO-BENCH: Can Large Language Models Leverage Domain Knowledge in Software Development?","created":"2026-01-19","cited_by_count":5,"area":null},{"id":"2508.04329","title":"Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning","created":"2025-08-06","cited_by_count":4,"area":null},{"id":"2512.05865","title":"Intrinsically Interpretable Attention via Sparse Post-Training","created":"2025-12-05","cited_by_count":4,"area":null},{"id":"2602.09492","title":"Beware of the Batch Size: Hyperparameter Bias in Evaluating LoRA","created":"2026-02-10","cited_by_count":4,"area":null},{"id":"2509.07177","title":"Towards EnergyGPT: A Large Language Model Specialized for the Energy Sector","created":"2025-09-08","cited_by_count":3,"area":null},{"id":"2502.11330","title":"System Message Generation for User Preferences using Open-Source Models","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2505.06150","title":"A Scaling Law for Token Efficiency in LLM Fine-Tuning Under Fixed Compute Budgets","created":"2025-05-09","cited_by_count":1,"area":null},{"id":"2507.04173","title":"Efficient Detection of Intermittent Job Failures Using Few-Shot Learning","created":"2025-07-05","cited_by_count":1,"area":null},{"id":"2509.13047","title":"Multi-Model Synthetic Training for Mission-Critical Small Language Models","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2512.09434","title":"CourtPressGER: A German Court Decision to Press Release Summarization Dataset","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2601.02764","title":"Netflix Artwork Personalization via LLM Post-training","created":"2026-01-06","cited_by_count":1,"area":null},{"id":"2605.04468","title":"Stabilizing LLM Supervised Fine-Tuning via Explicit Distributional Control","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2512.03053","title":"Mitigating hallucinations and omissions in LLMs for invertible problems: An application to hardware logic design automation","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2604.06262","title":"From Exposure to Internalization: Dual-Stream Calibration for In-context Clinical Reasoning","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2606.10706","title":"Unifying Data, Memory, and Compute Efficiency in LLM training: A Survey","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2609.22943","title":"Token Utility Is Selection-Conditioned: Coupled Selection of Prompt Context and Response Supervision for Instruction Tuning","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.32020","title":"A Benchmark for LLM's Understanding of Middle School and High School Science Topics","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}