Výsledky vyhledávání - "Sahami, Mehran"

Report

The GPT Surprise: Offering Large Language Model Chat in a Massive Coding Class Reduced Engagement but Increased Adopters Exam Performances

Autor: Nie, Allen, Chandak, Yash, Suzara, Miroslav, Ali, Malika, Woodrow, Juliette, Peng, Matt, Sahami, Mehran, Brunskill, Emma, Piech, Chris

Large language models (LLMs) are quickly being adopted in a wide range of learning experiences, especially via ubiquitous and broadly accessible chat interfaces like ChatGPT and Copilot. This type of interface is readily available to students and tea

Externí odkaz: http://arxiv.org/abs/2407.09975

Zobrazit plný text záznamu

Report

SimGrade: Using Code Similarity Measures for More Accurate Human Grading

Autor: Johnson-Yu, Sonja, Bowman, Nicholas, Sahami, Mehran, Piech, Chris

While the use of programming problems on exams is a common form of summative assessment in CS courses, grading such exam problems can be a difficult and inconsistent process. Through an analysis of historical grading patterns we show that inaccurate

Externí odkaz: http://arxiv.org/abs/2403.14637

Zobrazit plný text záznamu

Report

Deep Knowledge Tracing

Autor: Piech, Chris, Spencer, Jonathan, Huang, Jonathan, Ganguli, Surya, Sahami, Mehran, Guibas, Leonidas, Sohl-Dickstein, Jascha

Knowledge tracing---where a machine models the knowledge of a student as they interact with coursework---is a well established problem in computer supported education. Though effectively modeling student knowledge would have high educational impact,

Externí odkaz: http://arxiv.org/abs/1506.05908

Zobrazit plný text záznamu

Report

Learning Program Embeddings to Propagate Feedback on Student Code

Autor: Piech, Chris, Huang, Jonathan, Nguyen, Andy, Phulsuksombati, Mike, Sahami, Mehran, Guibas, Leonidas

Providing feedback, both assessing final work and giving hints to stuck students, is difficult for open-ended assignments in massive online classes which can range from thousands to millions of students. We introduce a neural network method to encode

Externí odkaz: http://arxiv.org/abs/1505.05969

Zobrazit plný text záznamu

Report

Automatic Classification of Text Databases through Query Probing

Autor: Ipeirotis, Panagiotis, Gravano, Luis, Sahami, Mehran

Many text databases on the web are "hidden" behind search interfaces, and their documents are only accessible through querying. Search engines typically ignore the contents of such search-only databases. Recently, Yahoo-like directories have started

Externí odkaz: http://arxiv.org/abs/cs/0003043

Zobrazit plný text záznamu