Skip to main content
HBT-INC-0236 · Dimension INC · Incentives

Retrieval-Augmented Generation (RAG)

Generate based on retrieved documents, not just trained weights.

Workflow·AI-Behavioral Coupling·Grade C·draft· enriching…
In one paragraph

Retrieval-Augmented Generation (RAG) is generate based on retrieved documents, not just trained weights. It sits in the Incentives dimension (INC) of the Human Behavior Taxonomy™ as element HBT-INC-0236, within the Workflow family. The core principle: generate based on retrieved documents, not just trained weights. In incentive terms, it matters because it changes the payoff people perceive before they choose — which means it can be designed for, or exploited.

Scientific Definition

Generate based on retrieved documents, not just trained weights.

Plain-English Definition

Generate based on retrieved documents, not just trained weights.

Feynman Explanation

Memory the model didn't have to memorize.

Core Principle

Generate based on retrieved documents, not just trained weights.

Mechanisms

Psychological

Pending editorial review.

Behavioral Economic

Pending editorial review.

Neurological

Pending editorial review.

Evolutionary

Pending editorial review.

Sociological

Pending editorial review.

Computational

Pending editorial review.

Systems

Pending editorial review.

Inputs (Triggers)

Pending editorial review.

Outputs (Behaviors)

Pending editorial review.

Behavioral Signature

Memory the model didn't have to memorize.

Examples

Everyday
  • Enterprise chatbots grounded in internal docs.
Modern (Organizational)
  • Standard pattern for enterprise LLM deployment.
Historical

Pending editorial review.

Lab Commentary

Original analysis from The Incentives Lab — how this element behaves inside real payoff structures.

Why this element matters to incentive design

When this element shows up in a diagnostic, the instinct is to train people out of it. Training rarely moves it. The mechanism underneath it operates in the Incentives dimension — what makes behavior more or less likely?. You can recognize it in the field by its signature: memory the model didn't have to memorize. Every element in the Incentives dimension changes the perceived payoff of an action before the action happens, which is exactly where incentive design has leverage.

How it gets exploited

Left undesigned, standard pattern for enterprise LLM deployment. It is amplified whenever standard pattern for enterprise LLM deployment. Inside organizations that shows up as standard pattern for enterprise LLM deployment. The pattern is the same one Goodhart's Law describes: the measurable proxy attracts the effort, and the purpose behind it quietly loses funding.

How the Lab designs around it

The redesign move is to quality of retrieval matters more than quality of generation. The leverage is not in explaining the behavior to people. It is in changing what the behavior earns.

Famous Experiments

Pending editorial review.

Design Principles

  • Quality of retrieval matters more than quality of generation.

Measurement Approaches

Pending editorial review.

Evidence

Evidence Grade
C (A strongest → E speculative)
Replication
★★☆☆☆
Intervention Confidence
3 / 5
Consensus
Pending editorial review (HBT v1.0 auto-seed).
Limitations
Pending editorial review (HBT v1.0 auto-seed).
Open Research Questions

Pending editorial review.

Primary References

Pending editorial review.

Signature Section

The Perverse Incentive Lens™

How this behavior is exploited — and how to redesign around it.

Exploitation
Standard pattern for enterprise LLM deployment.
Amplifying Incentives
Standard pattern for enterprise LLM deployment.
Org Failure Modes
Standard pattern for enterprise LLM deployment.
Societal Failure Modes
Pending editorial review (HBT v1.0 auto-seed).
Ethical Considerations
Pending editorial review (HBT v1.0 auto-seed).
Redesign Strategies
Quality of retrieval matters more than quality of generation.
Diagnostic Questions
  • Quality of retrieval matters more than quality of generation.
Warning Signs

Pending editorial review.

Red Flags

Pending editorial review.

Intervention Playbook
Individual
Quality of retrieval matters more than quality of generation.
Team
Pending editorial review (HBT v1.0 auto-seed).
Organization
Pending editorial review (HBT v1.0 auto-seed).
Policy
Pending editorial review (HBT v1.0 auto-seed).
AI Implications
Detection
Pending editorial review (HBT v1.0 auto-seed).
Measurement
Pending editorial review (HBT v1.0 auto-seed).
Mitigation
Pending editorial review (HBT v1.0 auto-seed).
Responsible Use
Pending editorial review (HBT v1.0 auto-seed).

Interactive Mini Network

Click any neighbor to re-center the graph and follow the threads of connection.

HBT-INC-0236 · INC
Retrieval-Augmented Generation (RAG)
RGAgAgentAWAI-First Workflow De…CDConcept DriftCWContext WindowDDData DriftEmEmbeddingEDEval DriftEFEvaluation Framework…ILIn-Context LearningLBLatency Budget

Knowledge Graph Neighbors

Where Retrieval-Augmented Generation (RAG) is cited in the corpus

Questions about Retrieval-Augmented Generation (RAG)

What is Retrieval-Augmented Generation (RAG)?
Retrieval-Augmented Generation (RAG) is generate based on retrieved documents, not just trained weights. It sits in the Incentives dimension (INC) of the Human Behavior Taxonomy™ as element HBT-INC-0236, within the Workflow family. The core principle: generate based on retrieved documents, not just trained weights. In incentive terms, it matters because it changes the payoff people perceive before they choose — which means it can be designed for, or exploited.
What is an example of Retrieval-Augmented Generation (RAG)?
Standard pattern for enterprise LLM deployment. The Incentives Lab catalogs everyday, organizational, and historical instances of this element on its Human Behavior Taxonomy™ page (HBT-INC-0236).
How is Retrieval-Augmented Generation (RAG) exploited?
Standard pattern for enterprise LLM deployment.
How do you design around Retrieval-Augmented Generation (RAG)?
Quality of retrieval matters more than quality of generation.
Which behavioral dimension does Retrieval-Augmented Generation (RAG) belong to?
Retrieval-Augmented Generation (RAG) is classified in the Incentives dimension (INC) of the Human Behavior Taxonomy™, family "Workflow", class "AI-Behavioral Coupling". Its permanent identifier is HBT-INC-0236 and its evidence grade is C.

Version History

v1.1.0 · 2026-06-28Initial auto-seed from corpus.