让文档通过多步思考生成更精准的向量表示，提升检索效果。
Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking
- 用多步推理逐步优化文档向量，代替单一固定向量。
- 在多个基准上超越现有方法，显著提升检索准确率。
- 适合需要高精度文档匹配的研究者与工程应用。
近期稠密检索器越来越多地利用大语言模型（LLM）强大的文本理解能力，将查询和文档编码到共享嵌入空间以实现高效检索。然而，现有大多数方法对每个文档仅使用单一嵌入表示，难以充分捕捉其多方面语义，从而限制了匹配精度。本文提出基于刻意思考的稠密检索器（Debater），通过引入分步思考机制，迭代式地优化文档嵌入。Debater采用链式反思（Chain-of-Deliberation）机制，持续改进文档表示；并进一步使用自蒸馏机制，识别并融合最具信息量的思考步骤，生成统一嵌入。实验结果表明，Debater在多个检索基准上显著优于现有方法，展现出更优的准确性和鲁棒性。代码与数据集已开源：https://github.com/OpenBMB/DEBATER。
原文摘要 · Abstract (English)
Recent dense retrievers increasingly leverage the robust text understanding capabilities of Large Language Models (LLMs), encoding queries and documents into a shared embedding space for effective retrieval. However, most existing methods represent each document with a single embedding, which is less effective at capturing its multifaceted semantics and thereby limits matching accuracy. In this paper, we propose Deliberate Thinking based Dense Retriever (Debater), a novel approach that enhances document representations by incorporating a step-by-step thinking process. Debater introduces a Chain-of-Deliberation mechanism, which iteratively refines document embeddings through a continuous chain-of-thought. To integrate information from various thinking steps, Debater further employs a Self Distillation mechanism that identifies and fuses the most informative steps into a unified embedding. Experimental results show that Debater significantly outperforms existing methods across several retrieval benchmarks, demonstrating superior accuracy and robustness. All codes and datasets are available at https://github.com/OpenBMB/DEBATER.
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。