个人记忆RAG中LINE对话历史检索：搜索表示与混合检索评估
原标题：LINE Conversation History Retrieval for Personal Memory RAG: Evaluating Search Representations and Hybrid Retrieval
AI 摘要
本研究针对个人记忆RAG，以单一用户的LINE聊天记录为对象，将358,896条消息分割为22,329个时间连贯的块，并构建了raw_text、summary和embedding_text三种搜索表示。通过对比BM25、稠密向量检索及线性混合检索，发现embedding_text_bm25在单一检索器中表现最佳，而embedding_text_bm25与embedding_text_vector的混合配置在100个评估问题上达到Recall@5=0.697。研究指出，对于跨时间和对话分布的聚合问题，扁平块级检索效果有限，但该研究为探索性单用户研究，未评估最终答案生成。
正文节选
LINE Conversation History Retrieval for Personal Memory RAG: Evaluating Search Representations and Hybrid Retrieval Akito Hattori Independent Researcher, Tokyo, Japan August 2026 Abstract 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 representa