Imagine All The Relevance: Scenario-Profiled Indexing with Knowledge Expansion for Dense Retrieval
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909693032529920 |
|---|---|
| author | Lee, Sangam Heo, Ryang Kang, SeongKu Lee, Dongha |
| author_facet | Lee, Sangam Heo, Ryang Kang, SeongKu Lee, Dongha |
| contents | 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 retrieval performance across various query types and dense retrievers. It also enhances the retrieval experience for users through scenario and offers valuable contextual information for LLMs in retrieval-augmented generation (RAG). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23033 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Imagine All The Relevance: Scenario-Profiled Indexing with Knowledge Expansion for Dense Retrieval Lee, Sangam Heo, Ryang Kang, SeongKu Lee, Dongha Information Retrieval 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 retrieval performance across various query types and dense retrievers. It also enhances the retrieval experience for users through scenario and offers valuable contextual information for LLMs in retrieval-augmented generation (RAG). |
| title | Imagine All The Relevance: Scenario-Profiled Indexing with Knowledge Expansion for Dense Retrieval |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2503.23033 |