liveBook · Manning

RECOMP

As explained in Retrieval Augmented Generation, The Foundational Ideas

RECOMP is a retrieval-augmented generation framework that trains compressor models to optimize downstream task performance and selectively omit unhelpful retrieved context.

RECOMP (Retrieve, Compress, Prepend) is a retrieval-augmented generation framework that trains compressor models offline to improve downstream task performance. Unlike generic pruning, it uses exact match and F1 signals and may refuse to add context when retrieved documents are unhelpful. section 13.4

RECOMP provides two compression strategies:

  • The extractive compressor selects useful sentences from retrieved documents and stitches them together. section 13.4
  • The abstractive compressor reads across documents and writes a shorter passage that may not appear verbatim in any source. section 13.4
  • Selective augmentation addresses retrieval misses: instead of producing a misleading summary from irrelevant documents, the compressor can return nothing. section 13.4

Cross-document drug interaction

Suppose one retrieved document describes a drug's mechanism and another describes a second medication's contraindications. An extractive compressor can preserve relevant sentences from both; an abstractive compressor can synthesize a sentence stating the resulting interaction when neither source states that claim alone. section 13.4

RECOMP targets a limitation of token-level pruning: once sentences and entities begin to fragment, removing individual tokens cannot preserve meaning or combine facts. Its learned rewriting and refusal behavior trade additional model training for stronger compression and safer handling of irrelevant retrieval. section 13.1.1 section 13.4

How Retrieval Augmented Generation, The Foundational Ideas covers it

How deep it goes
Explains offline task-optimized training, extractive and abstractive variants, refusal behavior, and cross-document synthesis without implementation details.
Examples
Uses a cross-document drug interaction scenario to contrast sentence selection with synthesized answer-bearing passages.
What it assumes
Assumes familiarity with retrieved documents, generators, and retrieval-augmented generation while contrasting RECOMP with token pruning.
What you can do after
Understand when extractive selection, abstractive synthesis, or selective refusal fits a retrieved-context compression problem.
How it connects
Connects retrieval-augmented generation with context compression, token-level pruning, extractive compression, 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.