liveBook · Manning

Extractive compressor

As explained in Retrieval Augmented Generation, The Foundational Ideas

An extractive compressor is a compressor model that selects and combines useful sentences from retrieved documents without generating new wording.

An extractive compressor selects useful sentences from retrieved documents and stitches them together without generating new wording. It reduces context before a downstream generator consumes it. section 13.1.1 section 13.4

RECOMP trains the compressor offline against downstream task performance, using exact match and F1 rather than perplexity or generic quality measures. The compressor may also refuse when the retrieved documents contain nothing useful, avoiding misleading prompts. section 13.4

Use the extractive approach when:

  • Each retrieved document already contains a self-contained answer, so preserving the strongest sentences is sufficient. section 13.4
  • The answer requires combining facts that no individual source states, prefer an abstractive compressor instead. section 13.4
  • Avoid treating compression as automatically reliable: misleading compressed prompts can be worse than injecting nothing. section 13.4

Cross-document drug interaction

Suppose retrieval returns one document describing a drug's mechanism and another describing a second medication's contraindications. An extractive compressor can retain relevant sentences from both, but cannot state the interaction if neither source states it directly; an abstractive compressor can synthesize that combined claim. section 13.4

How Retrieval Augmented Generation, The Foundational Ideas covers it

How deep it goes
Explains sentence selection, offline task optimization, refusal, and cross-document limits without detailing model internals.
Examples
Uses self-contained question answering and a multi-document drug-interaction scenario to contrast extraction with synthesis.
What it assumes
Assumes retrieved documents and a downstream generator, while distinguishing extraction from newly generated compression.
What you can do after
Evaluate whether sentence extraction suits a self-contained answer or whether cross-document synthesis requires an abstractive compressor.
How it connects
Connects retrieval-augmented generation with context compression, token pruning, and abstractive compression.

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.