Gender prompts shift feedback stance: female students receive affective, first-person, empathy-oriented feedback while male students receive objective, task-oriented critique¶

Claim · All claims
Evidence · 1 study · causal r2 · q2
Currency · no dated study recorded · checked against its sources 2026-10-17 (automated, 1 of 1 entry) · not reviewed by a person

Subclaims¶

q2 i? Feedback for students identified as female often used first-person pronouns and affective language positioning the model as personally engaged, and more often encouraged linking arguments to empathy and relational responsibility; feedback for male students was more objective and task-oriented, focusing on evidence, reasoning, and clarity. → Tan et al. 2026

Evidence¶

Tan et al. 2026¶

Mei Tan, Lena Phalen, and Dorottya Demszky. 2026. Marked Pedagogies: Examining Linguistic Biases in Personalized Automated Writing Feedback. In LAK 2026: 16th International Learning Analytics and Knowledge Conference (LAK 2026). ACM, New York, NY, USA. doi:10.1145/3785022.3785113

q2 · i? · causal · r2

Lexical comparison of female- versus male-prompted feedback for the same essays (Table 4: consider, love, empathy, our versus try, proofread, evidence, claim), with representative comments quoted from GPT-4o, GPT-3.5, and Llama models. No effect size is printed for the qualitative pattern.

"Feedback for students identified as female often used first-person pronouns and affective language that positioned the model as person- ally engaged with the student’s work"

Discussion¶

Learner Variables¶

• Gender — moderator: an instructional effect differs by group

Related Claims¶

• LLM feedback for students marked by race, language, disability, gender, or motivation shows positive feedback bias and feedback withholding bias — more praise and less substantive critique than for unmarked counterparts — related
• Motivation prompts shift feedback tone: unmotivated students receive enthusiastic, collaborative encouragement while motivated students receive direct, higher-level critique — related
• Bias transfer is asymmetric: prompt condition affects agency in female-target essays but not male-target essays, suppressing female agency while male writing remains stable — related
• Instructors use more first-person and second-person pronouns and more questions than LLMs in feedback comments — related
• Students assisted by a gender-biased LLM produce career-plan essays with a significantly larger male-female agentic gap than students in neutral-LLM and no-AI control conditions — related
• LLM feedback sentiment tracks assigned scores: low scores come with more criticism, high scores with more praise — related
• The editorial reports epistemic stance as an integrated unit of analysis for online discussion, with learning manifested in evolving shifts of stance objects (Park et al.) — related
• Automatically coded dialogue acts distinguish male and female students' online communication — related
• Gender related to students' emotions but showed no significant effects on math grades, while intelligence and SES related positively to grades — related