基于主题覆盖的检索方法，提升大模型上下文学习的准确性
Topic Coverage-based Demonstration Retrieval for In-Context Learning
- 根据测试输入所需主题，动态筛选覆盖关键知识的示例
- 在多个数据集上使上下文学习准确率平均提升5.2%以上
- 适合需要高精度少样本推理的应用场景
上下文学习的效果高度依赖于示范例的选择是否全面覆盖任务所需知识。现有方法多基于嵌入相似性或生成概率检索，常导致无关或冗余示例。本文提出TopicK框架，通过识别测试输入所需的细粒度主题，并评估模型对这些主题的知识掌握程度，迭代选择能填补知识空白且主题覆盖不足的示范例。实验验证了TopicK在多种数据集和开源/闭源大模型上的有效性，显著提升上下文学习性能。代码已公开于https://github.com/WonbinKweon/TopicK_EMNLP2025。
原文摘要 · Abstract (English)
The effectiveness of in-context learning relies heavily on selecting demonstrations that provide all the necessary information for a given test input. To achieve this, it is crucial to identify and cover fine-grained knowledge requirements. However, prior methods often retrieve demonstrations based solely on embedding similarity or generation probability, resulting in irrelevant or redundant examples. In this paper, we propose TopicK, a topic coverage-based retrieval framework that selects demonstrations to comprehensively cover topic-level knowledge relevant to both the test input and the model. Specifically, TopicK estimates the topics required by the input and assesses the model's knowledge on those topics. TopicK then iteratively selects demonstrations that introduce previously uncovered required topics, in which the model exhibits low topical knowledge. We validate the effectiveness of TopicK through extensive experiments across various datasets and both open- and closed-source LLMs. Our source code is available at https://github.com/WonbinKweon/TopicK_EMNLP2025.
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。