An empirical study of 1,023 CoT-code pairs shows that 76.4% of LLM-generated CoTs are low quality and that CoT correctness does not guarantee code correctness.
https://deepmind
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Are They All Good? Evaluating the Quality of CoTs in LLM-based Code Generation
An empirical study of 1,023 CoT-code pairs shows that 76.4% of LLM-generated CoTs are low quality and that CoT correctness does not guarantee code correctness.