Unlike traditional dense retrievers, SPIKE explicitly models the implicit relevance between document and potential information needs, not just surface similarity.
SPIKE effectively connects query-document pairs across different formats such as code snippets, enabling semantic alignment despite format differences.
By providing scenario explanations, SPIKE makes results more comprehensible and useful for real-world users and LLMs.
Using a efficient 3B scenario generator, which is applied offline to build a scenario-profiled index
Overview of SPIKE framework. (1) SPIKE define Scenario and generate it with high-performing large LLM. (2) Then, it construct scenario-augmented training set, and use this to optimize the efficient student LLM. During inference, (3) SPIKE considers scenariolevel relevance alongside document-level relevance to retrieve the documents.
SPIKE significantly enhances retrieval performance across diverse models and domains — all with a 3B scenario generator which is applied offline.
Retrieval Accuracy Gains
+20.7% (E5-Mistral)
+18.6% (SFR)
Consistent improvements on reasoning-intensive benchmarks like BRIGHT.
Human-Preferred Results
SPIKE was consistently preferred across various criteria such as usefulness.
SPIKE enhances retrieval experience for real-world users.
Boosts RAG Performance
Enhances answer generation for LLMs such as Claude-3.5 and LLaMA3-70B.
SPIKE provides valuable additional context for LLMs in RAG.