用多角度大模型生成查询，提升对话搜索的个性化与准确率
IRLab@iKAT24: Learned Sparse Retrieval with Multi-aspect LLM Query Generation for Conversational Search
- 通过多视角LLM生成查询，捕捉对话上下文
- 结合稀疏检索与交叉编码器，性能超越人工重写
- 适合研究对话搜索、个性化检索的开发者
iKAT 2024 主题聚焦于可适应用户个人知识的对话助手。任务包含基于个人文本知识库（PTKB）的段落排序与回复生成。针对对话上下文理解难题，我们探索使用大型语言模型（LLMs）作为查询重写工具。具体而言，提交方案采用MQ4CS框架实现多视角查询生成，并进一步融合基于SPLADE架构的学识稀疏检索，搭配强健的交叉编码器模型。我们还提出一种替代原有交错策略的新方法：在重排序阶段聚合多个视角。实验表明，将多视角查询生成与先进检索及重排序模型结合，能有效提升性能。结果证明该方法在个性化对话搜索中具有优势，利用LLM实现查询重写中的个性化，表现优于人类重写。
原文摘要 · Abstract (English)
The Interactive Knowledge Assistant Track (iKAT) 2024 focuses on advancing conversational assistants, able to adapt their interaction and responses from personalized user knowledge. The track incorporates a Personal Textual Knowledge Base (PTKB) alongside Conversational AI tasks, such as passage ranking and response generation. Query Rewrite being an effective approach for resolving conversational context, we explore Large Language Models (LLMs), as query rewriters. Specifically, our submitted runs explore multi-aspect query generation using the MQ4CS framework, which we further enhance with Learned Sparse Retrieval via the SPLADE architecture, coupled with robust cross-encoder models. We also propose an alternative to the previous interleaving strategy, aggregating multiple aspects during the reranking phase. Our findings indicate that multi-aspect query generation is effective in enhancing performance when integrated with advanced retrieval and reranking models. Our results also lead the way for better personalization in Conversational Search, relying on LLMs to integrate personalization within query rewrite, and outperforming human rewrite performance.
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。