Claims

LLM use for code generation is significantly negatively correlated with student final grades

Claim · All claims
Evidence · 1 study · causal r1 · q3
Currency · newest study 2024 · not yet checked against its sources · not reviewed by a person

Subclaims

Reading the evidence codes

q is the design tier, i the impact, n the sample, and the kind with its r the rigour judged within that kind: what each code means.

This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.

q3 i? Use of LLMs for generating code correlates negatively with final grades (Spearman's rho = -0.305, p = 0.045). → Jošt 2024

Evidence

Jošt 2024

Jošt, G.; Taneski, V.; Karakatič, S. (2024). The Impact of Large Language Models on Programming Education and Student Learning Outcomes. Appl. Sci. 14, 4115. https://doi.org/10.3390/app14104115

q3 · i? · causal · r1

One-sided Spearman correlation with bootstrap confidence intervals from the same thirty-two-participant experiment; the confidence interval (−0.595, −0.058) excludes zero. The article prints "Spearman's rho = −0.305, p = 0.045".

"the analysis revealed a significant inverse relationship between the use of LLMs for generating code and final grades (Spearman's rho = −0.305, p = 0.045)"

Discussion

Page metadata
Field Value
type claim
id llm-code-generation-negative-correlation-grades
title LLM use for code generation is significantly negatively correlated with student final grades
description LLM use for code generation is significantly negatively correlated with student final grades
status review
evidence_strength moderate
newest_evidence 2024
generated by process:wiki-ingest on 2026-10-12
trust unverified — no one has confirmed this page's content
sources 1 — jošt-2024

Frontmatter is the page's machine-readable record — see the Schema & Guide.