liveBook · Manning

Peak-then-decline behavior

As explained in Retrieval Augmented Generation, The Foundational Ideas

Peak-then-decline behavior is a performance pattern in which adding context improves results up to a point and then reduces them.

Peak-then-decline behavior occurs when additional retrieved context improves answer quality only up to a small optimum, after which accumulated noise reduces performance. It makes retrieval depth a model-specific production decision rather than a simple recall maximization problem. section 15.0

The pattern changes how a RAG system should be evaluated and tuned:

  • Measure the reader's optimal retrieval depth instead of assuming that larger k produces better answers. section 15.0
  • Separate stability from scalability: performance may remain consistent near an optimum without continuing to improve as context grows. section 15.0 section 15.9
  • Treat higher retriever recall cautiously when the reader is noise-sensitive; semantically similar passages can distract more than less relevant passages. section 15.0

A learned retrieval gate

A lightweight gate can adjust retrieval influence per token, suppressing passages that add noise and helping a noise-sensitive reader avoid the declining side of its performance curve. section 15.4.1

How Retrieval Augmented Generation, The Foundational Ideas covers it

How deep it goes
Defines the performance curve, contrasts it with improvement-then-plateau behavior, and links it to RSS and RSC without deriving them.
Examples
Compares FLAN-T5, GPT-3.5, LLaMA, and Claude, and contrasts BM25 with ColBERT under noisy retrieval.
What it assumes
Assumes familiarity with RAG, retrieved passages, reader models, and retriever quality; distinguishes stability from scalability.
What you can do after
Diagnose reader sensitivity and tune retrieval depth or gating rather than maximizing retrieved context by default.
How it connects
Connects reader models, retrieval depth, retriever recall, noise robustness, RSS, RSC, and learned retrieval gates.

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.