The article discusses the growing use of large language models (LLMs) to assess student discourse at scale, noting that current validation methods—such as expert annotations and F1 scores—often ignore the contextual and cultural nuances of student language. It argues that these practices inadequately capture the experiences of racially and linguistically marginalized youth, and proposes re‑contextualizing classroom conversations and involving students as epistemic authorities. A case study with multilingual 8th‑grade math students demonstrates misalignments between student self‑interpretations and LLM outputs, underscoring the need for youth participation in validating LLM‑based measures.
arXiv:2607. 28630v1 Announce Type: cross Abstract: Generative AI (GenAI) holds significant promise for advancing educational equity among ethnic minority students by broadening access to learning resources and mitigating linguistic barriers.
arXiv:2607. 28889v1 Announce Type: cross Abstract: Qualitative researchers increasingly encounter interaction corpora whose scale exceeds what manual coding alone can address, and large language models (LLMs) are frequently proposed as analytic assistants.
arXiv:2609.06095v1 Announce Type: cross Abstract: Motivation: Undergraduate computing students increasingly turn to generative AI (GenAI) tools to understand abstract concepts through analogies. Anal...
arXiv:2606. 09831v1 Announce Type: cross Abstract: As classroom cohorts expand, team teaching is increasingly used to integrate the expertise and pedagogical perspectives of multiple teachers.
EduDial is a large-scale multi-turn teacher‑student dialogue corpus covering 345 core knowledge points and 34,250 dialogue sessions, designed around Bloom’s taxonomy and ten questioning strategies such as situational, ZPD, and metacognitive questioning. The dataset includes differentiated teaching strategies for students at varying cognitive levels to provide targeted guidance. Using EduDial, the authors trained EduDial‑LLM 32B and introduced an 11‑dimensional evaluation framework that measures teaching quality and content quality, showing that most mainstream LLMs struggle with student‑centered teaching while EduDial‑LLM outperforms all baselines across all metrics.
The study explores how undergraduate computing students in Saudi Arabia perceive AI‑generated writing feedback when they are explicitly told that ChatGPT, not a human instructor, produced the score and comments. Through qualitative reflections, four themes emerged: students found the feedback useful for surface‑level revisions, recognized AI’s contextual and pedagogical limits, trusted the feedback conditionally—separating its utility from its authority—and reaffirmed the human instructor’s role as the ultimate grading authority. The findings highlight a clear distinction students make between feedback usefulness and evaluative authority, treating them as separate judgments rather than opposing ends of a single approval scale.
arXiv:2607. 00211v1 Announce Type: new Abstract: Epistemic thinking plays a central role in students' learning processes when applying generative artificial intelligence (GenAI), particularly in programming contexts where learners must construct queries, evaluate and validate AI-generated outputs, and regulate problem-solving strategies.
The study analyzes 604 real‑time classroom poll questions from 47 live sessions, aligning each poll with lecture transcripts and attendance data. It finds that 89% of poll answers can be located in the lecture context, revealing that many polls serve attention‑checking functions only visible when contextualized. The majority of questions are lower‑order and fit into seven instructional functions, with student engagement high overall but uneven, and students often misjudge their own correctness.
arXiv:2606. 15766v1 Announce Type: new Abstract: A central pedagogical value evaluated in AI tutor benchmarks is scaffolding: guiding students through graduated steps toward a solution.
arXiv:2603. 22793v2 Announce Type: replace Abstract: Classroom AI systems increasingly infer high-level educational states such as engagement, confusion, collaboration, participation, and instructional quality from multimodal and linguistic signals.
arXiv:2604. 21137v3 Announce Type: replace-cross Abstract: Analyzing the reasoning patterns of students in science classrooms is critical for understanding knowledge construction mechanism and improving instructional practice to maximize cognitive engagement, yet manual coding of classroom discourse at scale remains prohibitively labor-intensive.
The paper investigates which demographic attributes large language models (LLMs) default to when annotating text without explicit demographic cues. By comparing non‑demographic, placebo‑conditioned, and demographic‑conditioned prompts on politeness and offensiveness tasks in the POPQUORN dataset, the authors find that LLMs exhibit notable gender, race, and age influences in their annotations. This contrasts with earlier studies that reported no such effects, highlighting the importance of considering demographic bias in LLM‑based annotation workflows.