AI safety and alignment · MLD-0961

Proxy objective

A measurable substitute for a harder-to-measure real objective.

Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.

Original example

Use a judge score as a proxy for usefulness.

Original caveat

A correlated proxy can fail under strong optimization.

Context and aliases

Level: Advanced. Stages: Training · Evaluation · Research · Governance.

Tags: Safety · RL · SLM · LLM.

Aliases: Proxy metric.

Related concepts

Concepts linking here

Original references

Open original record, export or annotate →