Publication Date
In 2025 | 6 |
Descriptor
Natural Language Processing | 5 |
Artificial Intelligence | 3 |
Classification | 2 |
Computational Linguistics | 2 |
Computer Software | 2 |
Connected Discourse | 2 |
Correlation | 2 |
Cues | 2 |
Essays | 2 |
High School Students | 2 |
Profiles | 2 |
More ▼ |
Source
Grantee Submission | 6 |
Author
Danielle S. McNamara | 2 |
Andrew Avitabile | 1 |
Andrew Kwok | 1 |
Andrew Potter | 1 |
Angela Eeds | 1 |
Ashwin T. S. | 1 |
Ben Clarke | 1 |
Brendan Bartanen | 1 |
Brian Heseung Kim | 1 |
Caitlin Snyder | 1 |
Christian Doabler | 1 |
More ▼ |
Publication Type
Reports - Research | 5 |
Journal Articles | 2 |
Reports - Evaluative | 1 |
Education Level
Audience
Location
Texas | 1 |
Laws, Policies, & Programs
Assessments and Surveys
Digit Span Test | 1 |
Stanford Early School… | 1 |
Wechsler Preschool and… | 1 |
What Works Clearinghouse Rating
Large Language Models and Intelligent Tutoring Systems: Conflicting Paradigms and Possible Solutions

Punya Mishra; Danielle S. McNamara; Gregory Goodwin; Diego Zapata-Rivera – Grantee Submission, 2025
The advent of Large Language Models (LLMs) has fundamentally disrupted our thinking about educational technology. Their ability to engage in natural dialogue, provide contextually relevant responses, and adapt to learner needs has led many to envision them as powerful tools for personalized learning. This emergence raises important questions about…
Descriptors: Artificial Intelligence, Intelligent Tutoring Systems, Technology Uses in Education, Educational Technology

Clayton Cohn; Surya Rayala; Caitlin Snyder; Joyce Horn Fonteles; Shruti Jain; Naveeduddin Mohammed; Umesh Timalsina; Sarah K. Burriss; Ashwin T. S.; Namrata Srivastava; Menton Deweese; Angela Eeds; Gautam Biswas – Grantee Submission, 2025
Collaborative dialogue offers rich insights into students' learning and critical thinking. This is essential for adapting pedagogical agents to students' learning and problem-solving skills in STEM+C settings. While large language models (LLMs) facilitate dynamic pedagogical interactions, potential hallucinations can undermine confidence, trust,…
Descriptors: STEM Education, Computer Science Education, Artificial Intelligence, Natural Language Processing
Linh Huynh; Danielle S. McNamara – Grantee Submission, 2025
We conducted two experiments to assess the alignment between Generative AI (GenAI) text personalization and hypothetical readers' profiles. In Experiment 1, four LLMs (i.e., Claude 3.5 Sonnet; Llama; Gemini Pro 1.5; ChatGPT 4) were prompted to tailor 10 science texts (i.e., biology, chemistry, physics) to accommodate four different profiles…
Descriptors: Natural Language Processing, Profiles, Individual Differences, Semantics
Andrew Potter; Mitchell Shortt; Maria Goldshtein; Rod D. Roscoe – Grantee Submission, 2025
Broadly defined, academic language (AL) is a set of lexical-grammatical norms and registers commonly used in educational and academic discourse. Mastery of academic language in writing is an important aspect of writing instruction and assessment. The purpose of this study was to use Natural Language Processing (NLP) tools to examine the extent to…
Descriptors: Academic Language, Natural Language Processing, Grammar, Vocabulary Skills
Brendan Bartanen; Andrew Kwok; Andrew Avitabile; Brian Heseung Kim – Grantee Submission, 2025
Heightened concerns about the health of the teaching profession highlight the importance of studying the early teacher pipeline. This exploratory, descriptive article examines preservice teachers' expressed motivation for pursuing a teaching career. Using data from a large teacher education program in Texas, we use a natural language processing…
Descriptors: Career Choice, Teaching (Occupation), Teacher Education Programs, Preservice Teachers
Taylor Lesner; Ben Clarke; Derek Kosty; Geovanna Rodriguez; Elizabeth L. Budd; Christian Doabler – Grantee Submission, 2025
This secondary analysis of data from a randomized control trial of an early mathematics intervention, ROOTS, explored whether patterns of intervention response were best categorized by the typical response/non-response binary or a more complex framework with additional response profiles. Participants included kindergarten students at risk for…
Descriptors: Mathematics Instruction, Response to Intervention, At Risk Students, Kindergarten