让检索模型理解对话上下文，提升多轮搜索准确性
Learning Contextual Retrieval for Robust Conversational Search
- 用上下文感知嵌入，突出当前问题在对话中的位置
- 基于高质量重写查询训练，精准捕捉用户意图
- 无需额外计算开销，适合实际部署的对话搜索场景
有效的对话式搜索需要对多轮对话中用户意图有深入理解。用户常使用缩写或中途切换话题，给传统检索器带来挑战。尽管查询重写技术能提升清晰度，但通常因增加自回归步骤而带来显著计算开销。此外，虽然基于大语言模型的检索器表现强劲，但在多轮设置下未显式优化意图追踪，常在话题漂移或上下文模糊时失效。为此，我们提出 ContextualRetriever，一种新型基于大语言模型的检索器，直接将对话上下文融入检索过程。该方法引入：(1) 上下文感知嵌入机制，突出当前查询在对话历史中的重要性；(2) 基于高质量重写查询的意图引导监督；(3) 保留基础大模型生成能力的训练策略。在多个对话搜索基准上的广泛评估表明，ContextualRetriever 显著优于现有方法，且不增加推理开销。
原文摘要 · Abstract (English)
Effective conversational search demands a deep understanding of user intent across multiple dialogue turns. Users frequently use abbreviations and shift topics in the middle of conversations, posing challenges for conventional retrievers. While query rewriting techniques improve clarity, they often incur significant computational cost due to additional autoregressive steps. Moreover, although LLM-based retrievers demonstrate strong performance, they are not explicitly optimized to track user intent in multi-turn settings, often failing under topic drift or contextual ambiguity. To address these limitations, we propose ContextualRetriever, a novel LLM-based retriever that directly incorporates conversational context into the retrieval process. Our approach introduces: (1) a context-aware embedding mechanism that highlights the current query within the dialogue history; (2) intent-guided supervision based on high-quality rewritten queries; and (3) a training strategy that preserves the generative capabilities of the base LLM. Extensive evaluations across multiple conversational search benchmarks demonstrate that ContextualRetriever significantly outperforms existing methods while incurring no additional inference overhead.
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。