Marked Pedagogies: Examining Linguistic Biases in Personalized Automated Writing Feedback

• URL: http://arxiv.org/abs/2603.12471v1
• Date: Thu, 12 Mar 2026 21:44:25 GMT
• Title: Marked Pedagogies: Examining Linguistic Biases in Personalized Automated Writing Feedback
• Abstract summary: Using 600 eighth-grade persuasive essays, we generated feedback under prompt conditions embedding gender, race/ethnicity, learning needs, achievement, and motivation.<n>Our results reveal systematic, stereotype-aligned shifts in feedback conditioned on presumed student attributes--even when essay content was identical.<n>Across attributes, models tailored not only what content was emphasized but also how writing was judged and how students were addressed.
• Score: 6.51172312374669
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• The Role of Implicit and Explicit Demographic Signals in Large Language Model-based Student Assessment [24.32015609344653]
  Large Language Models are now common in student assessment, but we know little about how student demographics affect their use.<n>We set up controlled prompts to test 1) explicit demographic effects, where we mention demographic details directly, and 2) implicit effects, where we use conversation history as a demographic signal.<n>In both explicit and implicit cases, the models pick up on demographic cues and can change their scoring, feedback, and answers accordingly.
  arXiv  Detail & Related papers  (2026-09-15T11:07:26Z)
• Consistently Good vs. Occasionally Great: A Rubric for Open-Ended Feedback Quality from Humans and Machines [3.4020399898813145]
  We focus on feedback for open-ended short answer questions in introductory programming.<n>We develop a five-criteria rubric grounded in educational literature for evaluating feedback quality.
  arXiv  Detail & Related papers  (2026-08-22T08:48:53Z)
• Beyond the Traceback: Using LLMs for Adaptive Explanations of Programming Errors [52.619793817715326]
  We present a multi-stage crowdsourced study evaluating skill-targeted, LLM-generated Python error messages.<n>We show that while LLM-rewritten messages significantly improved subjective evaluations, these perceived gains did not translate into statistically significant improvements in objective debug performance.<n>This highlights a critical human-AI complementarity gap: explanations that feel better to users do not necessarily make them more effective debuggers.
  arXiv  Detail & Related papers  (2026-08-21T09:14:28Z)
• Data Annotations as Pedagogical Hints: From Subjective Labels to Critical Thinking [15.463313028798767]
  Machine learning courses often use pre-labeled datasets, hiding the subjectivity of human annotation.<n>This creates students with an overly trusting view of AI data and models, undervaluing interpretive diversity.<n>We investigated whether manual data annotation tasks teach students about subjective labeling.
  arXiv  Detail & Related papers  (2026-07-22T13:51:56Z)
• Exposía: Academic Writing Assessment of Exposés and Peer Feedback [56.428320613219306]
  We present Exposa, the first public dataset that connects writing and feedback assessment in higher education.<n>We use Exposa to benchmark state-of-the-art open-source large language models (LLMs) for two tasks: automated scoring of (1) the proposals and (2) the student reviews.
  arXiv  Detail & Related papers  (2026-01-10T11:33:26Z)
• Simulating Identity, Propagating Bias: Abstraction and Stereotypes in LLM-Generated Text [8.988787218035414]
  We investigate whether persona-prompting leads to different levels of linguistic abstraction when generating short texts linking socio-demographic categories with stereotypical or non-stereotypical attributes.<n>Our results confirm criticisms about the ecology of personas as representative of socio-demographic groups and raise concerns about the risk of propagating stereotypes.
  arXiv  Detail & Related papers  (2025-09-10T10:49:21Z)
• Help Me Write a Story: Evaluating LLMs' Ability to Generate Writing Feedback [57.200668979963694]
  We present a novel test set of 1,300 stories that we corrupted to intentionally introduce writing issues.<n>We study the performance of commonly used LLMs in this task with both automatic and human evaluation metrics.
  arXiv  Detail & Related papers  (2025-07-21T18:56:50Z)
• Can Reasoning Help Large Language Models Capture Human Annotator Disagreement? [84.32752330104775]
  Variation in human annotation (i.e., disagreements) is common in NLP.<n>We evaluate the influence of different reasoning settings on Large Language Model disagreement modeling.<n>Surprisingly, our results show that RLVR-style reasoning degrades performance in disagreement modeling.
  arXiv  Detail & Related papers  (2025-06-24T09:49:26Z)
• From Handwriting to Feedback: Evaluating VLMs and LLMs for AI-Powered Assessment in Indonesian Classrooms [10.687406183657275]
  We evaluate state-of-the-art VLMs and LLMs on over 14K handwritten answers from grade-4 classrooms in Indonesia.<n>Our dataset features naturally curly, diverse handwriting from real classrooms, posing realistic visual and linguistic challenges.
  arXiv  Detail & Related papers  (2025-06-05T09:41:09Z)
• Automated Assignment Grading with Large Language Models: Insights From a Bioinformatics Course [0.0]
  Natural language processing and large language models (LLMs) offer a promising solution by enabling the efficient delivery of personalized feedback.<n>Recent advances in natural language processing and large language models (LLMs) offer a promising solution by enabling the efficient delivery of personalized feedback.<n>Our results show that with well-designed prompts, LLMs can achieve grading accuracy and feedback quality comparable to human graders.
  arXiv  Detail & Related papers  (2025-01-24T13:59:14Z)
• LLM-as-a-Judge & Reward Model: What They Can and Cannot Do [2.2469442203227863]
  We conduct a comprehensive analysis of automated evaluators, reporting several key findings on their behavior. We discover that English evaluation capabilities significantly influence language-specific evaluation capabilities, enabling evaluators trained in English to easily transfer their skills to other languages. We find that state-of-the-art evaluators struggle with challenging prompts, in either English or Korean, underscoring their limitations in assessing or generating complex reasoning questions.
  arXiv  Detail & Related papers  (2024-09-17T14:40:02Z)
• Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Course [49.296957552006226]
  Using large language models (LLMs) for automatic evaluation has become an important evaluation method in NLP research. This report shares how we use GPT-4 as an automatic assignment evaluator in a university course with 1,028 students.
  arXiv  Detail & Related papers  (2024-07-07T00:17:24Z)
• Exploring LLM Prompting Strategies for Joint Essay Scoring and Feedback Generation [13.854903594424876]
  Large language models (LLMs) have demonstrated strong performance in generating coherent and contextually relevant text. This work explores several prompting strategies for LLM-based zero-shot and few-shot generation of essay feedback. Inspired by Chain-of-Thought prompting, we study how and to what extent automated essay scoring (AES) can benefit the quality of generated feedback.
  arXiv  Detail & Related papers  (2024-04-24T12:48:06Z)
• Improving the Validity of Automatically Generated Feedback via Reinforcement Learning [46.667783153759636]
  We propose a framework for feedback generation that optimize both correctness and alignment using reinforcement learning (RL)<n>Specifically, we use GPT-4's annotations to create preferences over feedback pairs in an augmented dataset for training via direct preference optimization (DPO)
  arXiv  Detail & Related papers  (2024-03-02T20:25:50Z)
• "Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters [97.11173801187816]
  Large Language Models (LLMs) have recently emerged as an effective tool to assist individuals in writing various types of content. This paper critically examines gender biases in LLM-generated reference letters.
  arXiv  Detail & Related papers  (2023-10-13T16:12:57Z)
• COFFEE: Counterfactual Fairness for Personalized Text Generation in Explainable Recommendation [56.520470678876656]
  bias inherent in user written text can associate different levels of linguistic quality with users' protected attributes. We introduce a general framework to achieve measure-specific counterfactual fairness in explanation generation.
  arXiv  Detail & Related papers  (2022-10-14T02:29:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.