Gear: Generation Augmented Retrieval

Abstract

Document retrieval techniques are essential for developing large-scale information systems. The common approach involves using a bi-encoder to compute the semantic similarity between a query and documents. However, the scalar similarity often fail to reflect enough information, hindering the interpretation of retrieval results. In addition, this process primarily focuses on global semantics, overlooking the finer-grained semantic relationships between the query and the document's content. In this paper, we introduce a novel method, \(\textbf\{Ge\}\)neration \(\textbf\{A\}\)ugmented \(\textbf\{R\}\)etrieval (\(\textbf\{GeAR\}\)), which not only improves the global document-query similarity through contrastive learning, but also integrates well-designed fusion and decoding modules. This enables GeAR to generate relevant context within the documents based on a given query, facilitating learning to retrieve local fine-grained information. Furthermore, when used as a retriever, GeAR does no

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score2.79
• arxiv keyliu2025gear

Related papers

• Advancing Similarity Search With Genai: A Retrieval Augmented Generation Approach (2024)0.00
• Attention Grounded Enhancement For Visual Document Retrieval (2025)0.00
• Generative Retrieval Meets Multi-graded Relevance (2024)2.26
• Hetarag: Hybrid Deep Retrieval-augmented Generation Across Heterogeneous Data Stores (2025)3.27
• Are We On The Right Way For Assessing Document Retrieval-augmented Generation? (2025)0.00
• Generative Dense Retrieval: Memory Can Be A Burden (2024)4.52
• Generative Retrieval As Multi-vector Dense Retrieval (2024)8.60
• Gradient Augmented Information Retrieval With Autoencoders And Semantic Hashing (2018)0.00