LLM-generated feedback is more comprehensive in volume than human feedback but is sometimes too generic, abstract, or misaligned with the assigned grade¶
Claim · All claims
Evidence · 1 study · reviewr3·q3
Currency · newest study 2026 · checked against its sources 2026-10-20 (automated, 1 of 1 entry) · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly
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.
q2 i? Regarding feedback quality specifically, GenAI was worse than humans 5 times, comparable 3 times, and better 3 times in the reviewed comparisons. → Marcin Jukiewicz and Michał Wyrwa 2026
Evidence¶
Marcin Jukiewicz and Michał Wyrwa 2026¶
Marcin Jukiewicz and Michał Wyrwa. (2026). Can ChatGPT Replace the Teacher in Assessment? A Review of Research on the Use of Large Language Models in Grading and Providing Feedback. Appl. Sci. 2026, 16, 680. https://doi.org/10.3390/app16020680
q3 · i? · review · r3
The review tallies feedback-quality comparisons separately from grading comparisons across the included studies. These are printed counts; no effect size is reported.
"Regarding just the feedback quality, GenAI was worse 5 times, comparable 3 times, and better than humans in 3 cases."
Discussion¶
Related Claims¶
- Some students struggled to use Ecree's and MI Write's automated feedback — the general claim this finding bears on, with the studies behind it
- Business Writing students valued AI feedback for higher-order and sentence-level comments but found it sometimes too general, while appreciating peers' contextual knowledge — related
- ChatGPT-3.5 feedback on EAP argumentative essays aligns closely with human instructor scoring and identifies surface-level issues, but is less effective on rhetorical structure and contextual nuance — related
- Students perceived peer group feedback as contextually rich but sometimes subjective, and ChatGPT-4o feedback as more objective and well structured but occasionally lacking contextual sensitivity — related
- LLM grading performance relative to human graders is mixed: comparable in 12 reviewed cases, worse in 11, with the strongest alignment on short, straightforward tasks — a broader claim this one bears on
- First-year EAP students prefer a hybrid feedback model combining AI-generated comments with instructor feedback over either source alone — related
- LLMs perform worse on complex, open-ended, or subjective assignments than on short, clearly formulated answers — a broader claim this one bears on
- Teachers find Ecree's feedback less useful when it does not align with their typical content sequence and grading standards — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
llm-feedback-volume-vs-quality |
title |
LLM-generated feedback is more comprehensive in volume than human feedback but is sometimes too generic, abstract, or misaligned with the assigned grade |
description |
LLM-generated feedback is more comprehensive in volume than human feedback but is sometimes too generic, abstract, or misaligned with the assigned grade |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
source_checked |
2026-10-20 |
recheck_by |
2029 |
generated |
by process:wiki-ingest on 2026-10-12 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — marcin-jukiewicz-and-michał-wyrwa-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.