让神经记忆听懂人话，按指令选择性学习新知识
Tell Me What To Learn: Generalizing Neural Memory to be Controllable in Natural Language
- 用自然语言指令控制模型学什么、忘什么
- 在多源异构信息中实现精准选择性记忆
- 适合医疗、客服等需灵活适应的场景
现代机器学习模型部署于多样且动态变化的环境中，需持续适应新任务与不断更新的知识。持续微调和上下文学习成本高且不稳定，而神经记忆方法可实现轻量级更新并最小化遗忘。然而，现有神经记忆模型通常假设单一固定目标和同质信息流，使用户无法控制模型随时间记住或忽略的内容。为此，我们提出一种通用神经记忆系统，可根据自然语言中的学习指令进行灵活更新。该方法使智能体能够从异构信息源中选择性学习，适用于医疗、客户服务等固定目标记忆更新不足的场景。
原文摘要 · Abstract (English)
Modern machine learning models are deployed in diverse, non-stationary environments where they must continually adapt to new tasks and evolving knowledge. Continual fine-tuning and in-context learning are costly and brittle, whereas neural memory methods promise lightweight updates with minimal forgetting. However, existing neural memory models typically assume a single fixed objective and homogeneous information streams, leaving users with no control over what the model remembers or ignores over time. To address this challenge, we propose a generalized neural memory system that performs flexible updates based on learning instructions specified in natural language. Our approach enables adaptive agents to learn selectively from heterogeneous information sources, supporting settings, such as healthcare and customer service, where fixed-objective memory updates are insufficient.
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。