logo
Loading...
LARGE LANGUAGE MODELS CANNOT SELF-CORRECT REASONING YET

Computer Science

LARGE LANGUAGE MODELS CANNOT SELF-CORRECT REASONING YET

J. Huang, X. Chen, et al.

This paper critically examines self-correction in Large Language Models, focusing on intrinsic self-correction—when a model tries to fix its own answers without external feedback. The authors find that LLMs often struggle to self-correct during reasoning and can even degrade after attempting fixes, and they offer directions for future research and applications. This research was conducted by Jie Huang, Xinyun Chen, Swaroop Mishra, Huaixiu Steven Zheng, Adams Wei Yu, Xinying Song, and Denny Zhou.... show more
Citation Metrics
Citations
33
Influential Citations
73
Reference Count
53
Citation by Year

Note: The citation metrics presented here have been sourced from Semantic Scholar and OpenAlex.

Related Publications

Explore these studies to deepen your understanding of the subject.

Confidence in the Reasoning of Large Language Models
Computer Science

Confidence in the Reasoning of Large Language Models

Y. Pawitan and C. Holmes

Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
Computer Science

Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation

J. Liu, S. Chunqiu, et al.

AI-AI bias: Large language models favor communications generated by large language models
Computer Science

AI-AI bias: Large language models favor communications generated by large language models

W. Laurito, B. Davis, et al.

DISSOCIATING LANGUAGE AND THOUGHT IN LARGE LANGUAGE MODELS
Linguistics and Languages

DISSOCIATING LANGUAGE AND THOUGHT IN LARGE LANGUAGE MODELS

K. Mahowald, I. A. Blank, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny