ModelRefs / Verbosity — AI Glossary

Verbosity — AI Glossary

The tendency of instruction-tuned models to produce longer, more elaborate responses than necessary, often to satisfy RLHF raters.

Overview

RLHF creates a verbosity bias: raters often prefer longer answers that appear thorough, even if a concise answer is better. Manifests as padding, unnecessary caveats, and restating the question. Addressed in Claude's constitution and GPT-4o by penalizing padding and rewarding conciseness. Verbosity increases token cost and latency.

Reference details

Topicprompting
Last reviewed2026-06-24

Continue your research

Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Verbosity — AI Glossary.

Frequently asked questions

What is Verbosity?

The tendency of instruction-tuned models to produce longer, more elaborate responses than necessary, often to satisfy RLHF raters.

What concepts are related to Verbosity?

Closely related concepts include sycophancy, instruction following, alignment.