In-Context Learning (ICL) is suffering from unsatisfactory performance and under-calibration due to high prior bias and unfaithful confidence. Some previous works fine-tuned language models for better ICL performance with enormous datasets and computing costs. In this paper, we propose NoisyICL, simply perturbing the model parameters by random noises to strive for better performance and calibration. Our experiments on 2 models and 12 downstream datasets show that NoisyICL can help ICL produce more accurate predictions. Our further analysis indicates that NoisyICL enables the model to provide more fair predictions, and also with less unfaithful confidence. Therefore, we believe that NoisyICL is an effective calibration of ICL. Our experimental code is uploaded to Github.

翻译：上下文学习（ICL）因高度先验偏差和不可靠置信度而面临性能不佳与校准不足的问题。先前部分研究通过海量数据集和计算成本对语言模型进行微调以提升ICL性能。本文提出NoisyICL方法，仅通过随机噪声扰动模型参数即可实现更优性能与校准效果。我们在2个模型和12个下游数据集上的实验表明，NoisyICL能够帮助ICL生成更准确的预测。进一步分析显示，NoisyICL促使模型提供更公平的预测，同时降低不可靠置信度。因此，我们认为NoisyICL是ICL的有效校准手段。本文实验代码已上传至Github。