# CRITIC

> CRITIC is a self-correction framework in which a model checks its output using external tools, such as web search or a code interpreter, critiques it based on what the tools return, and then revises it.

- Identifier: PTL-0119
- Category: Self-Critique & Verification
- Canonical URL: https://protologue.com/t/critic/
- Also known as: tool-interactive critiquing
- Introduced: 2023

## Description

Grounding the critique in tool feedback addresses the main weakness of intrinsic self-correction. The original work showed improvements on question answering, program synthesis, and reducing toxic output, and the same verify-then-revise loop is common in agent systems.

## Broader terms

- [Self-Correction](https://protologue.com/t/self-correction/)

## Related terms

- [Self-Refine](https://protologue.com/t/self-refine/)
- [Function Calling](https://protologue.com/t/function-calling/)
- [Code Execution Tool](https://protologue.com/t/code-execution-tool/)
- [Chain-of-Verification](https://protologue.com/t/chain-of-verification/)

## Sources

- Gou et al. (2023). CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing. https://arxiv.org/abs/2305.11738

## Cite this entry

Protologue. (2026). CRITIC. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0119). https://protologue.com/t/critic/

License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)