2 citations · 6 across the 8 of their papers we have counts for
8 papers
PromptNCE: Conditional Probabilities and PMI Using Only LLMs and Contrastive Estimation Prompts
Juliette Woodrow, Chris Piech
Estimating mutual information from text usually requires training a task-specific critic, which limits its use in low-data settings. We ask whether large language models can instea…
The Future of Feedback: How Can AI Help Transform Feedback to Be More Engaging, Effective, and Scalable?
Jennifer Meyer, Olaf Köller, Thorben Jansen +33
With digital learning environments becoming more prevalent, the ease with which generative AI enables the scalable production of real-time, automated feedback holds the potential t…
EducaSim: Interactive Simulacra for CS1 Instructional Practice
Cameron Mohne, Nicholas Vo, Dora Demszky +1
Role play is a high-impact mode of training that has demonstrated its effectiveness in improving learning outcomes. However, it is difficult to scale to teacher instruction due to…
Protecting and Promoting Human Agency in Education in the Age of Artificial Intelligence
Olga Viberg, Mutlu Cukurova, Rene F. Kizilcec +12
Human agency is crucial in education and increasingly challenged by the use of generative AI. This meeting report synthesizes interdisciplinary insights and conceptualizes four asp…
Handwritten Code Recognition for Pen-and-Paper CS Education
Md Sazzad Islam, Moussa Koulako Bala Doumbouya, Christopher D. Manning +1
Teaching Computer Science (CS) by having students write programs by hand on paper has key pedagogical advantages: It allows focused learning and requires careful thinking compared…
The GPT Surprise: Offering Large Language Model Chat in a Massive Coding Class Reduced Engagement but Increased Adopters Exam Performances
Allen Nie, Yash Chandak, Miroslav Suzara +6
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 Co…
From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation
Ali Malik, Stephen Mayhew, Chris Piech +1
We study the problem of controlling the difficulty level of text generated by Large Language Models (LLMs) for contexts where end-users are not fully proficient, such as language l…
TeachNow: Enabling Teachers to Provide Spontaneous, Realtime 1:1 Help in Massive Online Courses
Ali Malik, Juliette Woodrow, Chao Wang +1
One-on-one help from a teacher is highly impactful for students, yet extremely challenging to support in massive online courses (MOOCs). In this work, we present TeachNow: a novel…