Improving the Generalizability of Models of Collaborative Discourse Abstract We investigated methods to enhance the generalizability of large language models (LLMs) designed to classify dimensions of collaborative discourse during small group work.Our research utilized five diverse datasets that spanned various grade levels, demographic groups, collaboration settings, and curriculum units. We explored different model train-ing techniques with RoBERTa […]

Sense-Making with an AI-Enhanced Coaching Tool: A Think-Aloud Study Abstract We investigate the sense-making processes of instructional coaches who engage with an AI feedback tool, Hybrid Human-Agent Tutoring (HAT)platform, in the context of a high-dosage human tutoring program. HAT providesautomatic feedback on the discourse practices of tutors embedded in a coached-tutor model. This study describes the […]