提升复杂推理文档检索的嵌入模型，效果优于现有方法。
ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval
- 用新数据合成法生成8.2万条高质量训练样本，解决旧数据平庸问题。
- 设计自适应权重算法，动态调整样本训练强度，捕捉查询与文档深层语义。
- 在BRIGHT基准上刷新纪录，最大模型nDCG@10达38.1，适合推理密集型任务。
本文提出ReasonEmbed，一种专为复杂推理型文档检索设计的新文本嵌入模型。主要贡献包括：首先，提出ReMixer数据合成方法，克服以往合成数据集的平庸问题，实现大规模生成82,000条高质量训练样本；其次，设计Redapter自适应学习算法，根据样本推理强度动态调整其训练权重，使模型更有效捕捉查询与文档间的复杂语义关系；最后，在多个不同规模的骨干网络上实现ReasonEmbed，均在推理密集型检索任务中表现优异。特别地，ReasonEmbed-Qwen3-8B模型在BRIGHT基准上取得38.1的nDCG@10最高分，显著超越现有文本嵌入模型。相关资源将全面开源，以推动该领域研究进展。
原文摘要 · Abstract (English)
In this paper, we introduce ReasonEmbed, a novel text embedding model developed for reasoning-intensive document retrieval. Our work includes three key technical contributions. First, we propose ReMixer, a new data synthesis method that overcomes the triviality problem prevalent in previous synthetic datasets, enabling large-scale production of 82K high-quality training samples. Second, we design Redapter, a self-adaptive learning algorithm that dynamically adjusts training each sample's weight based on its reasoning intensity. This allows the model to effectively capture the complex semantic relationships between queries and documents. Third, we implement ReasonEmbed across multiple backbones of varying sizes, all of which achieve superior performance on reasoning-intensive retrieval tasks. Notably, our ReasonEmbed-Qwen3-8B model offers a record-high nDCG@10 score of 38.1 on the BRIGHT benchmark, which significantly outperforms existing text embedding models. We will fully open-source our created resources in ReasonEmbed to push forward the research advancement in this field.
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。