liveBook · Manning

Active correction

As explained in Retrieval Augmented Generation, The Foundational Ideas

Reactive correction is a retrieval pattern that audits an initial retrieval result and intervenes only when that result is inadequate.

Active correction audits an initial retrieval result and intervenes only when it is inadequate. A retrieval evaluator sends low-confidence results through a corrective web-search loop, targeting staleness and single-fact hallucination. section 11.4

Use active correction when retrieval reliability matters more than unconditionally expanding the search:

  • Keep the fast Correct path for adequate results; trigger web search only on the Incorrect path. section 11.4
  • Apply it to fact-checking and real-time validation, such as verifying whether someone meets UK PEP rules. section 11.4
  • Combine it with proactive planning when queries require decomposition, multi-hop logic, or heterogeneous retrieval. section 11.4
Table 11.1 Strategic selection matrix
Feature
CRAG (Corrective)
LevelRAG (Plan-and-Refine)
Primary Mechanism
Evaluation & Fallback
Decomposition & Hierarchical Search
Best Use Case
Fact-Checking, Real-time Validation
Complex Research, Multi-document Synthesis
Key Innovation
Decompose-then-Recompose
High-Level Logic Planning
Compliance Role
Screening ("Is X a PEP?")
Advisory ("Compare Policy A vs B")
Latency Profile
Low (Internal) / High (Web Fallback)
High (Iterative Planning)
Architecture
Component Add-on
Full System Architecture

Compare active correction with hierarchical planning across mechanism, use case, compliance role, latency, and architecture. section 11.4

How Retrieval Augmented Generation, The Foundational Ideas covers it

How deep it goes
Adds an evaluator and web-search loop to an existing retrieval pipeline, but stops short of full structural query planning.
Examples
Uses PEP verification and the UK PEP Rules query to illustrate low-confidence retrieval and targeted correction.
What it assumes
Assumes an existing retrieval pipeline and teaches query-time evaluation plus conditional fallback.
What you can do after
Apply it via an evaluator node and web-search tool that selectively correct low-confidence retrieval results.
How it connects
Connects retrieval-augmented generation with web search, fact-checking, proactive planning, and multi-hop reasoning.

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.