liveBook · Manning

Multi-document synthesis task

As explained in Retrieval Augmented Generation, The Foundational Ideas

Multi-document synthesis is the generation of an answer by integrating information from multiple source documents.

A multi-document synthesis task requires generating one answer by combining evidence scattered across several documents rather than extracting a single fact. It appears when no passage contains the complete answer, as in summarizing the drivers of Apple's revenue growth from evidence about iPhone sales, Services growth, and logistics. section 5.5

Fusion-in-Decoder (FiD) addresses this setting by independently encoding each passage and giving the decoder access to their separate representations. This can isolate evidence effectively, but synthesis still fails when one passage produces a disproportionately strong signal and dominates generation. section 5.5

Use the task structure to distinguish synthesis from single-fact retrieval:

  • Choose multi-document synthesis when the answer must aggregate partial evidence across documents, such as a news or research summary. section 5.6
  • Prefer a basic retrieval-augmented generation system for simple, single-fact lookups such as identifying a capital city. section 5.6
  • Expect FiD to help with many passages and complex question answering, while recognizing the cost of independently encoding each passage. section 5.6

Apple revenue-growth question

Given passages about strong iPhone sales, 20% Services growth, and resilient logistics, a successful synthesis should integrate all three drivers. General-purpose readers instead returned only “strong iPhone sales,” showing how extraction can replace synthesis when one signal dominates. section 5.5

How Retrieval Augmented Generation, The Foundational Ideas covers it

How deep it goes
Explains independent passage encoding, decoder synthesis, signal dominance, and the scalability trade-off without detailing implementation internals.
Examples
Demonstrates synthesis with Apple's revenue drivers and contrasts it with a successful single-fact multi-GPU strategy question.
What you can do after
Evaluate/understand when FiD-style processing is preferable to basic RAG and diagnose extraction caused by dominant passage signals.
How it connects
Connects to Fusion-in-Decoder, open-domain question answering, retrieval-augmented generation, multi-document summarization, fact checking, and listwise reranking.

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.