Large language models (LLMs) have shown impressive performance on downstream tasks by in-context learning (ICL), which heavily relies on the quality of demonstrations selected from a large set of annotated examples. Recent works claim that in-context learning is robust to noisy demonstrations in text classification. In this work, we show that, on text generation tasks, noisy annotations significantly hurt the performance of in-context learning. To circumvent the issue, we propose a simple and effective approach called Local Perplexity Ranking (LPR), which replaces the "noisy" candidates with their nearest neighbors that are more likely to be clean. Our method is motivated by analyzing the perplexity deviation caused by noisy labels and decomposing perplexity into inherent perplexity and matching perplexity. Our key idea behind LPR is thus to decouple the matching perplexity by performing the ranking among the neighbors in semantic space. Our approach can prevent the selected demonstrations from including mismatched input-label pairs while preserving the effectiveness of the original selection methods. Extensive experiments demonstrate the effectiveness of LPR, improving the EM score by up to 18.75 on common benchmarks with noisy annotations.

大型语言模型在文本生成任务中，噪声标注显著影响了上下文学习的性能，因此我们提出了一种名为本地困惑度排序（LPR）的简单有效方法，通过在语义空间中对邻居进行排序，以防止选择到不匹配的输入-标签对，同时保持原始选择方法的有效性。大量实验证明了LPR的有效性，将EM得分在带噪声注释的常见基准测试中提高了18.75个点。

关于文本生成中上下文学习的噪声鲁棒性