Instructors use more first-person and second-person pronouns and more questions than LLMs in feedback comments¶
Claim · All claims
Evidence · 1 study (2 entries) · associationalr1·q2
Currency · newest study 2026 · checked against its sources 2026-10-20 (automated, 2 of 2 entries) · 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? Human feedback has a higher density of first-person pronouns (1.26 vs. 0.03 per 100 words) and second-person pronouns (5.19 vs. 3.75 per 100 words) than LLM feedback. → Yijun Liu 2026
q2 i? Instructor feedback contains 0.85 questions per 100 words against 0.23 for LLMs. → Yijun Liu 2026 (2)
Evidence¶
Yijun Liu 2026¶
Yijun Liu, Yifan Song, John Gallagher, Sarah Sterman, Tal August. (2026). FOXGLOVE: Understanding Goal-Oriented and Anchored Writing Feedback from Experts and LLMs on Argumentative Essays. https://arxiv.org/abs/2606.06271 doi:10.48550/arxiv.2606.06271
q2 · i? · associational · r1
Pronoun-density analysis of FOXGLOVE feedback comments (§4.2.2), counting first- and second-person pronouns per 100 words. The article reports "Humans average 1.26 first-person pro- nouns per 100 words, compared with only 0.03 for LLMs", suggesting instructor feedback is more conversational.
"Humans average 1.26 first-person pro- nouns per 100 words, compared with only 0.03 for LLMs. Human instructors also use direct address more often: 5.19 vs. 3.75 second-person pronouns per 100 words."
Yijun Liu 2026 (2)¶
Yijun Liu, Yifan Song, John Gallagher, Sarah Sterman, Tal August. (2026). FOXGLOVE: Understanding Goal-Oriented and Anchored Writing Feedback from Experts and LLMs on Argumentative Essays. https://arxiv.org/abs/2606.06271
q2 · i? · associational · r1
Question-use analysis of FOXGLOVE feedback comments (§4.2.3), counting question marks per 100 words. The article reports "Instructor feedback contains0.85ques- tions per 100 words against just 0.23 for LLMs", with Claude Sonnet 4.5 closest to humans (0.62).
"Instructor feedback contains0.85ques- tions per 100 words against just 0.23 for LLMs."
Discussion¶
Related Claims¶
- LLMs and instructors agree broadly on where feedback belongs but diverge on exact sentence spans, with span overlap strongly goal-dependent and LLMs highlighting more of each essay — related
- LLM feedback receives higher expert ratings on six of seven quality dimensions, with tone the exception — related
- Instructors and LLMs distribute feedback similarly across the five argumentative goals, with Claim receiving the most feedback from both — related
- Gender prompts shift feedback stance: female students receive affective, first-person, empathy-oriented feedback while male students receive objective, task-oriented critique — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
instructors-more-pronouns-and-questions |
title |
Instructors use more first-person and second-person pronouns and more questions than LLMs in feedback comments |
description |
Instructors use more first-person and second-person pronouns and more questions than LLMs in feedback comments |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
source_checked |
2026-10-20 |
recheck_by |
2029 |
generated |
by process:wiki-ingest on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
sources |
2 — yijun-liu-2026, yijun-liu-2026-2 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.