In-context learning (ICL), which promotes inference with several demonstrations, has become a widespread paradigm to stimulate LLM capabilities for downstream tasks. Due to context length constraints, it cannot be further improved in spite of more training data, and general features directly from LLMs in ICL are not adaptive to the specific downstream task. In this paper, we propose a feature-adaptive and data-scalable in-context learning framework (FADS-ICL), which can leverage task-adaptive features to promote inference on the downstream task, with the supervision of beyond-context samples. Specifically, it first extracts general features of beyond-context samples via the LLM with ICL input form one by one, and introduces a task-specific modulator to perform feature refinement and prediction after fitting a specific downstream task. We conduct extensive experiments on FADS-ICL under varying data settings (4$\sim$128 shots) and LLM scale (0.8$\sim$70B) settings. Experimental results show that FADS-ICL consistently outperforms previous state-of-the-art methods by a significant margin under all settings, verifying the effectiveness and superiority of FADS-ICL. For example, under the 1.5B and 32 shots setting, FADS-ICL can achieve \textbf{+14.3} average accuracy from feature adaptation over vanilla ICL on 10 datasets, with \textbf{+6.2} average accuracy over the previous state-of-the-art method, and the performance can further improve with increasing training data. Code and data are publicly available at \url{https://github.com/jiahaozhenbang/FADS-ICL}.

翻译：上下文学习（ICL）通过提供若干示例促进推理，已成为激发大语言模型（LLM）在下游任务中能力的主流范式。然而，受限于上下文长度约束，即便增加训练数据也无法进一步提升性能，且ICL中直接来自LLM的通用特征无法适配特定下游任务。本文提出一种特征自适应与数据可扩展的上下文学习框架（FADS-ICL），该框架能够利用任务自适应特征，在超上下文样本的监督下促进下游任务的推理。具体而言，它首先通过LLM逐一提取超上下文样本的通用特征（采用ICL输入形式），并引入任务特定调制器，在适配特定下游任务后进行特征精炼与预测。我们在不同数据设置（4~128样本）和LLM规模（0.8~70B参数）下对FADS-ICL进行了广泛实验。结果表明，在所有设置下，FADS-ICL均以显著优势超越此前最先进方法，验证了其有效性与优越性。例如，在1.5B参数和32样本设置下，FADS-ICL通过特征自适应在10个数据集上较原始ICL平均准确率提升+14.3，较此前最先进方法平均准确率提升+6.2，且性能随训练数据增加持续提升。代码与数据已公开于 \url{https://github.com/jiahaozhenbang/FADS-ICL}。