ReFilter：弥合嵌入与LLM过滤的相似移动应用检索
ReFilter: Bridging Embeddings and LLM Filtering for Similar Mobile App Retrieval
浏览论文内容
中文总结 AI 辅助
ReFilter提出混合框架，先用嵌入检索语义相关应用，再用LLM过滤识别功能相似应用，实现90%的F1分数，平衡效率与准确性。
中文摘要 AI 辅助
检索相似移动应用（app）对于研究人员、开发者和终端用户至关重要。研究人员使用相似性检测来研究应用生态系统和趋势，开发者用于竞争对手分析，终端用户则用于聚焦的应用推荐。现有方法依赖基于嵌入的检索，这能捕获语义相似性，但无法识别功能相似的应用。据我们所知，此前没有工作将基于大语言模型（LLM）的过滤应用于此任务，原因是评估大量应用对的计算成本过高。为解决这一空白，我们提出ReFilter，一个混合框架，首先使用嵌入检索语义相关的候选应用，然后应用基于LLM的上下文过滤，以更高精度识别真正的功能相似应用。该设计平衡了效率与准确性，在检索相似应用时实现了90%的F1分数。通过提高应用替代品的相关性，ReFilter能够实现更准确的应用比较，并支持改进的生态系统理解、竞争对手分析和推荐。
英文摘要
Retrieving similar mobile applications (apps) is essential for researchers, developers, and end-users. Researchers use similarity detection to study app ecosystems and trends, developers for competitor analysis, and end-users for focused app recommendations. Existing approaches rely on embedding-based retrieval, which captures semantic similarity but fails to identify functionally similar apps. To our knowledge, no prior work has applied large language model (LLM)-based filtering to this task, due to the high computational cost of evaluating large numbers of app pairs. To address this gap, we propose ReFilter, a hybrid framework that first Retrieves semantically related candidate apps using embeddings and then applies LLM-based contextual Filtering to identify true functionally similar apps with higher precision. This design balances efficiency and accuracy, achieving an F1-score of 90% for retrieving similar apps. By improving the relevance of app alternatives, ReFilter enables more accurate app comparisons and supports improved ecosystem understanding, competitor analysis, and recommendations.
发表机构
- University of Toronto（多伦多大学）
- Université du Québec à Montréal（蒙特利尔大学）
机构由 AI 辅助整理，请以论文原文为准。
