Imagine All The Relevance: Scenario-profiled Indexing With Knowledge Expansion For Dense Retrieval

Abstract

Existing dense retrieval models struggle with reasoning-intensive retrieval task as they fail to capture implicit relevance that requires reasoning beyond surface-level semantic information. To address these challenges, we propose Scenario-Profiled Indexing with Knowledge Expansion (SPIKE), a dense retrieval framework that explicitly indexes implicit relevance by decomposing documents into scenario-based retrieval units. SPIKE organizes documents into scenario, which encapsulates the reasoning process necessary to uncover implicit relationships between hypothetical information needs and document content. SPIKE constructs a scenario-augmented dataset using a powerful teacher large language model (LLM), then distills these reasoning capabilities into a smaller, efficient scenario generator. During inference, SPIKE incorporates scenario-level relevance alongside document-level relevance, enabling reasoning-aware retrieval. Extensive experiments demonstrate that SPIKE consistently enhances

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylee2025imagine

Related papers

• Pseudo-relevance Feedback For Multiple Representation Dense Retrieval (2021)12.93
• SAGE: Structure Aware Graph Expansion For Retrieval Of Heterogeneous Data (2026)0.00
• Bixse: Improving Dense Retrieval Via Probabilistic Graded Relevance Distillation (2025)0.00
• Pseudo Relevance Feedback Is Enough To Close The Gap Between Small And Large Dense Retrieval Models (2025)0.00
• Deeperimpact: Optimizing Sparse Learned Index Structures (2024)0.00
• Enhancing The Ranking Context Of Dense Retrieval Methods Through Reciprocal Nearest Neighbors (2023)4.52
• Your Dense Retriever Is Secretly An Expeditious Reasoner (2025)0.00
• Learning To Retrieve: How To Train A Dense Retrieval Model Effectively And Efficiently (2020)0.00