ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval
It addresses the problem of retrieving documents requiring complex reasoning for AI and information retrieval applications, with incremental improvements through novel data synthesis and training methods.
The paper tackles reasoning-intensive document retrieval by introducing ReasonEmbed, a text embedding model that achieves a record-high nDCG@10 score of 38.1 on the BRIGHT benchmark, significantly outperforming existing models.
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.