49 citations · 75 across the 12 of their papers we have counts for
14 papers
Agreement Is Not Validity: Cross-Model LLM Consensus in Diagnosing Student Failure Modes in K-12 Math Tutoring Dialogue
Clayton Cohn, Joyce Fonteles, Kirk Vanacore +5
In K-12 mathematics tutoring, student-tutor dialogue provides rich evidence of learners' problem-solving processes and sources of difficulty. Learning analytics research increasing…
Examining Variation in How Guided AI Tutors Resolve Student Impasses
Bakhtawar Ahtisham, Kirk Vanacore, Alessandra Napoli +5
When a student is stuck, a tutor faces the assistance dilemma: help given too early can hinder productive struggle, while help withheld too long leaves the student in a frustrating…
A Theory-Guided LLM Pedagogical Agent Supporting Open-Ended STEM+C Learning
Clayton Cohn, Surya Rayala, Siyuan Guo +13
Open-ended learning environments (OELEs) can support STEM+C (science, technology, engineering, mathematics, and computing) inquiry through activities such as computational modeling…
Science Literacy: Generative AI as Enabler of Coherence in the Teaching, Learning, and Assessment of Scientific Knowledge and Reasoning
Xiaoming Zhai, James W. Pellegrino, Matias Rojas +4
This chapter examines the potential of generative AI in enhancing science literacy across the K-16+ grade span, including its benefits as well as the conceptual and practical chall…
BEAGLE: Behavior-Enforced Agent for Grounded Learner Emulation
Hanchen David Wang, Clayton Cohn, Zifan Xu +3
Simulating student learning behaviors in open-ended problem-solving environments holds potential for education research, from training adaptive tutoring systems to stress-testing p…
Evidence-Decision-Feedback: Theory-Driven Adaptive Scaffolding for LLM Agents
Clayton Cohn, Siyuan Guo, Surya Rayala +11
LLMs offer tremendous opportunities for pedagogical agents to help students construct knowledge and develop problem-solving skills, yet many of these agents operate on a "one-size-…
Using Large Language Models to Detect Socially Shared Regulation of Collaborative Learning
Jiayi Zhang, Conrad Borchers, Clayton Cohn +7
The field of learning analytics has made notable strides in automating the detection of complex learning processes in multimodal data. However, most advancements have focused on in…
LearnLens: An AI-Enhanced Dashboard to Support Teachers in Open-Ended Classrooms
Namrata Srivastava, Shruti Jain, Clayton Cohn +3
Exploratory learning environments (ELEs), such as simulation-based platforms and open-ended science curricula, promote hands-on exploration and problem-solving but make it difficul…
A Theory of Adaptive Scaffolding for LLM-Based Pedagogical Agents
Clayton Cohn, Surya Rayala, Namrata Srivastava +6
Large language models (LLMs) present new opportunities for creating pedagogical agents that engage in meaningful dialogue to support student learning. However, current LLM systems…
Personalizing Student-Agent Interactions Using Log-Contextualized Retrieval-Augmented Generation (RAG)
Clayton Cohn, Surya Rayala, Caitlin Snyder +10
Collaborative dialogue offers rich insights into students' learning and critical thinking, which is essential for personalizing pedagogical agent interactions in STEM+C settings. W…
CoTAL: Human-in-the-Loop Prompt Engineering for Generalizable Formative Assessment Scoring and Feedback
Clayton Cohn, Ashwin T S, Naveeduddin Mohammed +1
Large language models (LLMs) have created new opportunities to assist teachers and support student learning. While researchers have explored various prompt engineering approaches i…
Multimodal Methods for Analyzing Learning and Training Environments: A Systematic Literature Review
Clayton Cohn, Eduardo Davalos, Caleb Vatral +7
Recent technological advancements in multimodal machine learning--including the rise of large language models (LLMs)--have improved our ability to collect, process, and analyze div…
Towards A Human-in-the-Loop LLM Approach to Collaborative Discourse Analysis
Clayton Cohn, Caitlin Snyder, Justin Montenegro +1
LLMs have demonstrated proficiency in contextualizing their outputs using human input, often matching or beating human-level performance on a variety of tasks. However, LLMs have n…
A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students' Formative Assessment Responses in Science
Clayton Cohn, Nicole Hutchins, Tuan Le +1
This paper explores the use of large language models (LLMs) to score and explain short-answer assessments in K-12 science. While existing methods can score more structured math and…