用大模型重排序提升任务发现效率，解决幼教系统术语难搜的问题。
Rationale-Augmented Retrieval with Constrained LLM Re-Ranking for Task Discovery
- 融合词法、向量与受限大模型，实现容错语义搜索。
- 离线测试中命中率（Hit@K）达92%，零结果率降低67%。
- 适合教育类平台优化搜索体验，尤其有专业术语的系统。
针对使用GoEngage平台的早教项目，新员工或轮岗人员在主页查找合适任务（模块）时面临困难，原因包括领域专有术语（如IFPA、DRDP）、系统特有命名（如Application Pool），以及传统关键词搜索对拼写错误和词序变化的不敏感。本文提出一种实用的混合语义搜索系统，结合轻量级容错词法检索、基于嵌入的向量相似性匹配，以及受约束的大语言模型（LLM）重排序。该方法利用机构现有的任务资源库和知识库，通过低误报率保障可信度，具备应对术语变更的可演化性，并借助智能缓存、候选列表生成和优雅降级机制实现经济高效。提供了完整的框架，包括资源需求、分阶段实施策略及具体里程碑，离线评估采用定制测试集（包含Hit@K、Precision@K、Recall@K、MRR指标），在线评估则结合查询成功度、零结果率和停留时间代理指标。
原文摘要 · Abstract (English)
Head Start programs utilizing GoEngage face significant challenges when new or rotating staff attempt to locate appropriate Tasks (modules) on the platform homepage. These difficulties arise from domain-specific jargon (e.g., IFPA, DRDP), system-specific nomenclature (e.g., Application Pool), and the inherent limitations of lexical search in handling typos and varied word ordering. We propose a pragmatic hybrid semantic search system that synergistically combines lightweight typo-tolerant lexical retrieval, embedding-based vector similarity, and constrained large language model (LLM) re-ranking. Our approach leverages the organization's existing Task Repository and Knowledge Base infrastructure while ensuring trustworthiness through low false-positive rates, evolvability to accommodate terminological changes, and economic efficiency via intelligent caching, shortlist generation, and graceful degradation mechanisms. We provide a comprehensive framework detailing required resources, a phased implementation strategy with concrete milestones, an offline evaluation protocol utilizing curated test cases (Hit@K, Precision@K, Recall@K, MRR), and an online measurement methodology incorporating query success metrics, zero-result rates, and dwell-time proxies.
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。