7 papers
Utility-Preserving De-Identification for Math Tutoring: Investigating Numeric Ambiguity in the MathEd-PII Benchmark Dataset
Zhuqian Zhou, Kirk Vanacore, Bakhtawar Ahtisham +7
Large-scale sharing of dialogue data is key to advancing the science of teaching and learning, yet rigorous de-identification remains a major barrier. In mathematics tutoring trans…
Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts
Jinsook Lee, Kirk Vanacore, Zhuqian Zhou +2
Automated annotation of pedagogical dialogue is a high-stakes task where LLMs often fail without sufficient domain grounding. We present a domain-adapted RAG pipeline for tutoring…
The Digital Divide in Generative AI: Evidence from Large Language Model Use in College Admissions Essays
Jinsook Lee, Conrad Borchers, AJ Alvero +2
Large language models (LLMs) have become popular writing tools among students and may expand access to high-quality feedback for students with less access to traditional writing su…
LLM Reasoning Predicts When Models Are Right: Evidence from Coding Classroom Discourse
Bakhtawar Ahtisham, Kirk Vanacore, Zhuqian Zhou +2
Large Language Models (LLMs) are increasingly deployed to automatically label and analyze educational dialogue at scale, yet current pipelines lack reliable ways to detect when mod…
AI Annotation Orchestration: Evaluating LLM verifiers to Improve the Quality of LLM Annotations in Learning Analytics
Bakhtawar Ahtisham, Kirk Vanacore, Jinsook Lee +3
Large Language Models (LLMs) are increasingly used to annotate learning interactions, yet concerns about reliability limit their utility. We test whether verification-oriented orch…
Codebook-Injected Dialogue Segmentation for Multi-Utterance Constructs Annotation: LLM-Assisted and Gold-Label-Free Evaluation
Jinsook Lee, Kirk Vanacore, Zhuqian Zhou +3
Dialogue Act (DA) annotation typically treats communicative or pedagogical intent as localized to individual utterances or turns. This leads annotators to agree on the underlying a…