mlsanityData to 7 Oct 2026

Marked Pedagogies: Examining Linguistic Biases in Personalized Automated Writing Feedback

arXiv 2603.12471 ↗First posted 12 Mar 2026cs.CL cs.HCcited by 2

Not on the map. Why?

Abstract (arXiv)

Effective personalized feedback is critical to students' literacy development. Though LLM-powered tools now promise to automate such feedback at scale, LLMs are not language-neutral: they privilege standard academic English and reproduce social stereotypes, raising concerns about how "personalization" shapes the feedback students receive. We examine how four widely used LLMs (GPT-4o, GPT-3.5-turbo, Llama-3.3 70B, Llama-3.1 8B) adapt written feedback in response to student attributes. Using 600 eighth-grade persuasive essays from the PERSUADE dataset, we generated feedback under prompt conditions embedding gender, race/ethnicity, learning needs, achievement, and motivation. We analyze lexical shifts across model outputs by adapting the Marked Words framework. Our results reveal systematic, stereotype-aligned shifts in feedback conditioned on presumed student attributes--even when essay content was identical. Feedback for students marked by race, language, or disability often exhibited positive feedback bias and feedback withholding bias--overuse of praise, less substantive critique, and assumptions of limited ability. Across attributes, models tailored not only what content was emphasized but also how writing was judged and how students were addressed. We term these instructional orientations Marked Pedagogies and highlight the need for transparency and accountability in automated feedback tools.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 8 of its 59 references that are in the map. First posted on arXiv 12 Mar 2026.

Builds on

8 of 59 references.

References · 8

  1. 2023Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Modelscited by 204
  2. 2023"Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letterscited by 196
  3. 2024Large language models that replace human participants can harmfully misportray and flatten identity groupscited by 137
  4. 2024What's in a Name? Auditing Large Language Models for Race and Gender Biascited by 50
  5. 2024Enhancing LLM-Based Feedback: Insights from Intelligent Tutoring Systems and the Learning Sciencescited by 37
  6. 2024LLMs are Biased Teachers: Evaluating LLM Bias in Personalized Educationcited by 28
  7. 2024Beyond Binary Gender Labels: Revealing Gender Biases in LLMs through Gender-Neutral Name Predictionscited by 17
  8. 2024A Comprehensive Exploration of Personalized Learning in Smart Education: From Student Modeling to Personalized Recommendationscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Mitigating LLM biases toward spurious social contexts using direct preference optimizationcited by 0
  2. 2026Evaluating Feedback Focus and Pedagogical Adaptivity in LLM-Generated Feedback on Student Writingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Benchmarking Educational LLMs with Analytics: A Case Study on Gender Bias in Feedback
  2. 2026SEFORA: Student Essays with Feedback Corpus and LLM Feedback Evaluation Framework
  3. 2024Exploring LLM Prompting Strategies for Joint Essay Scoring and Feedback Generation
  4. 2026FOXGLOVE: Understanding Goal-Oriented and Anchored Writing Feedback from Experts and LLMs on Argumentative Essays
  5. 2026Contaminated Collaboration: Measuring Gender Bias Transfer in LLM-Assisted Student Writing
  6. 2025Exploring LLM-Generated Feedback for Economics Essays: How Teaching Assistants Evaluate and Envision Its Use
  7. 2025Poor Alignment and Steerability of Large Language Models: Evidence from College Admission Essays
  8. 2026Student Evaluation of Repeated AI Feedback Across a Semester of Writing ↗