Imagine All The Relevance: Scenario-Profiled Indexing with Knowledge Expansion for Dense Retrieval

Sangam Lee, Ryang Heo, SeongKu Kang, Dongha Lee

Keywords: Information Retrieval, Reasoning Intensive Retrieval, Dense Retrieval, Reasoning, LLM

TL;DR: We propose SPIKE, a dense retrieval framework that decomposes documents into scenarios.

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 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).

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 257