liveBook · Manning

Perspective shifting

As explained in Retrieval Augmented Generation, The Foundational Ideas

Perspective shifting is a query-generation technique that formulates searches from different facets or interpretations of an information need.

Perspective shifting formulates searches from distinct facets, sub-intents, or interpretations of one information need. In multi-query retrieval, an LLM expands the original question before retrieval, helping the system cover complex intent instead of relying on one semantic guess. section 8.0 section 8.2

Use perspective shifting to improve coverage without treating more queries as automatically better:

  • Target different needs rather than producing simple rephrasings, which often retrieve nearly identical documents. section 8.2
  • Run the variants in parallel, then merge their ranked results with Reciprocal Rank Fusion, which uses rank rather than incompatible retrieval scores. section 8.0 section 8.7
  • Start with three to five variants and evaluate latency, cost, coverage, and noise; additional queries can reduce quality. section 8.7

Winter jacket search

A standard search for “warm winter jacket” may return several near-duplicate warm-jacket documents. Perspective shifting generates queries about down parkas for extreme cold, lightweight insulated fleeces, waterproof ski jackets, and wool coats. Fused retrieval then surfaces distinct product categories, moving from narrow relevance matching toward discovery. section 8.5

You are a search assistant. The user has asked: "{question}". Generate {N} alternative search queries that target different facets, sub-intents, or interpretations of this question. Each query should explore a distinct angle so that together they cover the full intent. Return one query per line, no numbering.
 

Use this prompt pattern to instruct an LLM to produce one query per distinct facet, sub-intent, or interpretation. section 8.2

How Retrieval Augmented Generation, The Foundational Ideas covers it

How deep it goes
Explains facet decomposition, parallel retrieval, and RRF-based merging, while deferring model-specific rewriting internals.
Examples
Demonstrates college-laptop facets and winter-jacket retrieval with standard and fused result lists.
What it assumes
Assumes an LLM, a retrieval system, and ranked result lists, while teaching facet-oriented query generation through prompting.
What you can do after
Build multi-query retrieval that expands user intent and fuses ranked results for broader search coverage.
How it connects
Connects query expansion with RAG, vector search, Reciprocal Rank Fusion, hybrid search, and HyDE.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Retrieval Augmented Generation, The Foundational Ideas. The section links point to the parts of the book it draws on.