标记教学法：检验个性化自动写作反馈中的语言偏见
Marked Pedagogies: Examining Linguistic Biases in Personalized Automated Writing Feedback
AI总结：
研究探讨了四种常用LLM在不同学生属性下生成写作反馈的偏见，揭示了基于种族、语言等属性的反馈偏差，提出需提高自动反馈工具的透明度和问责性。
摘要：
有效的个性化反馈对学生语文发展至关重要。尽管LLM驱动的工具现在承诺大规模自动化此类反馈，但LLMs并非语言中性：它们优先考虑标准学术英语并复制社会刻板印象，引发对“个性化”如何影响学生反馈的担忧。我们检验了四种广泛使用的LLM（GPT-4o、GPT-3.5-turbo、Llama-3.3 70B、Llama-3.1 8B）如何根据学生属性调整写作反馈。使用600篇八年级说服性作文（来自PERSUADE数据集），我们生成了包含性别、种族/民族、学习需求、成绩和动机的提示条件下的反馈。通过适应Marked Words框架分析模型输出的词汇变化。我们的结果揭示了系统性的、与刻板印象一致的反馈变化，即使作文内容相同。被标记为种族、语言或残疾的学生往往表现出积极反馈偏见和反馈保留偏见——过度使用赞扬、较少实质性批评、以及对能力有限的假设。在所有属性中，模型不仅调整了强调的内容，还调整了写作的评判方式以及如何对待学生。我们称这些教学导向为“标记教学法”，并强调在自动反馈工具中需要提高透明度和问责性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
