轻量级方法缓解大模型流式学习中的知识遗忘问题。
Replay to Remember: Retaining Domain Knowledge in Streaming Language Models
- 结合LoRA与极小规模回放机制，实现高效持续学习。
- 实验显示，即使少量回放也能显著减少知识遗忘并部分恢复性能。
- 适合资源受限场景下需实时更新的AI应用开发人员。
大语言模型在持续学习中常面临灾难性遗忘问题，即新数据会损害已有知识。尽管已有回放缓冲和参数高效微调（如低秩适应，LoRA）等方法，但很少研究在严格计算与数据流约束下的实时领域适配。本文在医疗问答、遗传学和法律三个不同知识领域中，验证了一种结合LoRA与极小回放机制的轻量级方法。通过困惑度、语义相似度及GPT-based人类评估指标，量化了模型随时间的适应、遗忘与恢复能力。实验表明，尽管灾难性遗忘自然发生，但极小规模回放能显著稳定模型表现并部分恢复领域知识。该研究为资源受限的真实场景中部署可适应大模型提供了实用洞见。
原文摘要 · Abstract (English)
Continual learning in large language models (LLMs) typically encounters the critical challenge of catastrophic forgetting, where previously acquired knowledge deteriorates upon exposure to new data. While techniques like replay buffers and parameter-efficient tuning (e.g., Low-Rank Adaptation or LoRA) have been proposed, few studies investigate real-time domain adaptation under strict computational and data-stream constraints. In this paper, we demonstrate a lightweight method combining LoRA and a minimal replay mechanism in a realistic streaming setting across three diverse knowledge domains: medical question answering, genetics, and law. Using perplexity, semantic similarity, and GPT-based human-like evaluation metrics, we quantify the model's adaptation, forgetting, and recovery over time. Our experiments reveal that while catastrophic forgetting naturally occurs, even minimal replay significantly stabilizes and partially restores domain-specific knowledge. This study contributes practical insights for deploying adaptable LLMs in resource-constrained, real-world scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。