CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing

By Zhibin Gou, Zhihong Shao, Yeyun Gong, Yelong Shen, Yujiu Yang, Nan Duan, Weizhu Chen. 2023

809 citations recorded by the source corpus.

Recent developments in large language models (LLMs) have been impressive. However, these models sometimes show inconsistencies and problematic behavior, such as hallucinating facts, generating flawed code, or creating offensive and toxic content. Unlike these models, humans typically utilize external tools to cross-check and refine their initial content, like using a search engine for fact-checking, or a code interpreter for debugging. Inspired by this observation, we introduce a framework called CRITIC that allows LLMs, which are essentially"black boxes"to validate and progressively amend their own outputs in a manner similar to human interaction with tools. More specifically, starting with an initial output, CRITIC interacts with appropriate tools to evaluate certain aspects of the text, and then revises the output based on the feedback obtained during this validation process. Comprehensive evaluations involving free-form question answering, mathematical program synthesis, and toxicity reduction demonstrate that CRITIC consistently enhances the performance of LLMs. Meanwhile, our research highlights the crucial importance of external feedback in promoting the ongoing self-improvement of LLMs.

Subfields: Artificial Intelligence, Information Systems, Large Language Models, LLM Agents & Tool Use

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Jianfeng Gao
  2. Mohit Bansal
  3. Furu Wei
  4. Luke S. Zettlemoyer
  5. Percy Liang
  6. Hannaneh Hajishirzi
  7. Yejin Choi
  8. Graham Neubig

In Information Systems

  1. Huan Sun
  2. Denny Zhou
  3. Xinyun Chen
  4. Heng Ji
  5. Zhihong Shao
  6. Jie Huang
  7. Minlie Huang
  8. Yelong Shen

In Large Language Models

  1. Furu Wei
  2. Xinyun Chen
  3. Wenhu Chen
  4. Jie Huang
  5. Yao Fu
  6. Swaroop Mishra
  7. Tao Ge
  8. Zhihong Shao

In LLM Agents & Tool Use

  1. Minlie Huang
  2. Swaroop Mishra
  3. Furu Wei

Citations in the corpus