平衡合成数据与重放以增强任务特定能力
Balancing Synthetic Data and Replay for Enhancing Task-Specific Capabilities
AI总结：
本研究通过实证分析，在持续预训练中平衡合成数据与重放比例，以在有限计算预算下实现任务性能与知识保留的最优权衡，并提供实用指导。
摘要：
通过持续预训练使语言模型适应新任务面临一个基本权衡：模型必须学习新能力，同时避免对现有知识的灾难性遗忘。虽然先前的工作已经研究了合成数据生成技术，但在计算约束下平衡任务性能与知识保留的最优重放比例仍然知之甚少。我们提出了一项全面的实证研究，探讨在将语言模型适应新任务时，重放比例配置与计算预算之间的相互作用。以bAbI推理任务为目标，我们应用合成数据生成，并系统地评估不同的总token预算和重放比例配置。我们分析了它们对任务掌握和一般知识保留的影响。我们的实验揭示了一种最优配置，该配置平衡了任务特定性能与一般知识保留。基于我们的发现，我们提供了基于计算预算选择重放比例的实证指导方针，使从业者能够以显著降低的训练成本实现强大的任务适应。
英文摘要：
Adapting language models to new tasks through continued pretraining faces a fundamental trade-off: models must learn new capabilities while avoiding catastrophic forgetting of existing knowledge. While prior work has studied synthetic data generation techniques, the optimal replay ratios for balancing task performance and knowledge retention under computational constraints remain poorly understood. We present a comprehensive empirical study investigating the interplay between replay ratio configuration and computational budget when adapting language models to new tasks. Using the bAbI reasoning tasks as our target objective, we apply synthetic data generation and systematically evaluate different total token budgets and replay ratio configurations. We analyze their effects on both task mastery and general knowledge retention. Our experiments reveal an optimal configuration that balances task-specific performance with general knowledge retention. Based on our findings, we provide empirically-grounded guidelines for selecting replay ratios based on computational budget, enabling practitioners to achieve strong task adaptation with significantly reduced training costs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
