LINE Conversation History Retrieval for Personal Memory RAG: Evaluating Search Representations and Hybrid Retrieval

  • 类型:arxiv
  • 标识:2608.27809
  • 链接:http://arxiv.org/abs/2608.27809v1
  • 主分类:rag
  • 形态:method
  • TLDR:As an initial step toward personal memory retrieval-augmented generation (RAG) for large language models (LLMs), this study presents a retrieval-only case study over one user's LINE conversation history. We segmented 358,896 messages into 22,329 temporally coherent chunks and constructed three search representations: raw_text, a generated summary, and embedding_text, which combines a summary with a raw-text excerpt and other fixed text. We compared BM25, dense vector retrieval, and linear hybrid retrieval on 100 evaluation questions verified by a single annotator. Among individual retrievers,
  • 副分类:evaluation
  • 待LLM分类:否
  • 标题中文:基于 LINE 对话历史的个人记忆 RAG 检索:搜索表示与混合检索评估
  • TLDR中文:作为面向大语言模型 (LLM) 的个人记忆检索增强生成 (RAG) 研究的初步步骤,本文围绕单一用户的 LINE 对话历史开展纯检索案例研究。我们将 358,896 条消息切分为 22,329 个时序连贯片段,构建三种搜索表示:raw_text、生成的摘要,以及将摘要与原始文本片段及其他固定文本结合的 embedding_text。在经单一标注者核验的 100 个评估问题上对比 BM25、稠密向量检索与线性混合检索。在各独立检索器中,
  • 来源文件
  • /inbox/tom/_candidates/2026-09-01-rag-retrieval-reranking-candidates.json
  • /inbox/tom/_candidates/2026-09-01-agent-rag-longcontext-candidates.json