让大模型通过增强上下文更高效学习，且难以追溯训练素材。
On the Power of Context-Enhanced Learning in LLMs
- 用非自回归数据增强上下文进行梯度学习，模拟上下文学习机制。
- 在多步推理任务中，样本效率比传统方法高指数级提升。
- 学习信号更精准，且训练材料难以被检测或恢复，关乎数据安全。
我们提出大模型中的一种新范式——上下文增强学习，即在文本上进行标准的梯度学习，但上下文通过额外数据增强，这些数据不参与自回归梯度计算。该设定是典型上下文学习（ICL）的梯度类比，已在部分近期研究中出现。通过一个多步推理任务，在简化设置下证明：当模型具备上下文学习能力时，上下文增强学习相比标准学习具有指数级更高的样本效率。机制层面发现，其优势源于更精确的梯度学习信号。实验还表明，训练中使用的上下文材料极难被检测或恢复，可能对数据安全与版权保护带来影响。
原文摘要 · Abstract (English)
We formalize a new concept for LLMs, context-enhanced learning. It involves standard gradient-based learning on text except that the context is enhanced with additional data on which no auto-regressive gradients are computed. This setting is a gradient-based analog of usual in-context learning (ICL) and appears in some recent works. Using a multi-step reasoning task, we prove in a simplified setting that context-enhanced learning can be exponentially more sample-efficient than standard learning when the model is capable of ICL. At a mechanistic level, we find that the benefit of context-enhancement arises from a more accurate gradient learning signal. We also experimentally demonstrate that it appears hard to detect or recover learning materials that were used in the context during training. This may have implications for data security as well as copyright.
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。