I am a PhD student at Stanford University's Computer Science Department, advised by Diyi Yang and Dora Demszky. I also collaborate closely with Susanna Loeb. I develop machine learning (ML) and natural language processing (NLP) methods for real-world domains, with a focus on Education as a critical domain with profound societal impact. I tackle challenges that arise in human-human and human-AI interactions.
I'm on the academic and industry job market 2024-25. If you think I could be a good fit for your organization, please reach out!
My work introduces algorithms, benchmarks and large-scale interventions for scaling expertise, i.e., building language models that capture expert reasoning. My research is deployed in industry and directly improves the education of under-served students through partnerships I've cultivated during my Ph.D. at Stanford, including Title I school districts and several education companies, impacting 200,000+ students, 1,700+ teachers, 16,100+ tutors, in millions of tutoring sessions across the U.S., UK and India. My work is recognized by a Best Paper Award at CogSci, Best Paper Award at NeurIPS Cooperative AI, Best Paper Award at BEA, ICLR Oral, NSF Graduate Research Fellowship, Rising Star in Data Science, and Tools Competition Award.
I did my undergrad at MIT (2020) with Profs. Josh Tenenbaum, Jonathan How, Google Brain and Google Brain Robotics on multiagent systems & reinforcement learning. During my PhD, I interned at the Allen Institute for AI (AI2). Growing up, I was raised in Finland and Germany, was a passionate multilinguist in German (Abitur), Chinese (HSK Level 6), French (DELF B2), Spanish (DELE B2) and received the European plurilingual excellence award.
Please find all publications on my Google Scholar.
* denotes equal contributions.
Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertise PDF Preregistration Video Code
Rose E. Wang, Ana Ribeiro, Carly Robinson, Dora Demszky, Susanna Loeb.
Society for Research on Educational Effectiveness (SREE 2024), UChicago Becker Friedman Institute AI for Social Science Conference 2024, American Economic Association (AEA 2024).
Featured in MIT Technology Review, Education Week, the 74, K-12 Dive, MarkTechPost, Dan Meyer's blog, Stanford Accelerator for Learning.
🌁 Bridging the Novice-Expert Gap via Models of Decision-Making PDF Poster Video Code
Rose E. Wang, Qingyang Zhang, Carly Robinson, Susanna Loeb, Dora Demszky
North American Chapter of the Association for Computational Linguistics (NAACL 2024)
Invited Presentation at the National Student Support Accelerator Conference (2024).
Featured in Stanford HAI and Dan Meyer's blog
Edu-ConvoKit: An Open-Source Library for Education Conversation Data PDF Poster Video Code
Rose E. Wang, Dora Demszky
North American Chapter of the Association for Computational Linguistics (NAACL 2024)
Invited Presentation at Education Data Mining (EDM 2024) LLM for EdTech Workshop, National Tutoring Observatory, Learning Analytics Learning Network
How Tutors Share or Split Attention Across Students in Small-Group Tutoring
Qingyang Zhang*, Rose E. Wang*, Ana Ribeiro, Susanna Loeb, Dorottya (Dora) Demszky.
SREE 2024.
ScaffGen: Scaling High-Leverage Curriculum Scaffolding in Middle-School Mathematics PDF
Rizwaan Malik, Dorna Abdi, Rose E. Wang, Dora Demszky
Learning at Scale (L@S 2024); Under journal submission.
Winner of 2024 Tools Competition 🏆
Featured in The Learning Agency
Does Feedback on Talk Time Increase Student Engagement? Evidence from a Randomized Controlled Trial on a Math Tutoring Platform PDF
Dora Demszky, Rose E. Wang, Sean Geraghty, Carol Yu
Learning Analytics and Knowledge Conference (LAK '24)
Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertise PDF Preregistration Video Code
Rose E. Wang, Ana Ribeiro, Carly Robinson, Dora Demszky, Susanna Loeb.
Society for Research on Educational Effectiveness (SREE 2024), UChicago Becker Friedman Institute AI for Social Science Conference 2024, American Economic Association (AEA 2024).
Featured in MIT Technology Review, Education Week, the 74, K-12 Dive, MarkTechPost, Dan Meyer's blog, Stanford Accelerator for Learning.
🌁 Bridging the Novice-Expert Gap via Models of Decision-Making PDF Poster Video Code
Rose E. Wang, Qingyang Zhang, Carly Robinson, Susanna Loeb, Dora Demszky
North American Chapter of the Association for Computational Linguistics (NAACL 2024)
Invited Presentation at the National Student Support Accelerator Conference (2024).
Featured in Stanford HAI and Dan Meyer's blog
Edu-ConvoKit: An Open-Source Library for Education Conversation Data PDF Poster Video Code
Rose E. Wang, Dora Demszky
North American Chapter of the Association for Computational Linguistics (NAACL 2024)
Invited Presentation at Education Data Mining (EDM 2024) LLM for EdTech Workshop, National Tutoring Observatory, Learning Analytics Learning Network
How Tutors Share or Split Attention Across Students in Small-Group Tutoring
Qingyang Zhang*, Rose E. Wang*, Ana Ribeiro, Susanna Loeb, Dorottya (Dora) Demszky.
SREE 2024.
ScaffGen: Scaling High-Leverage Curriculum Scaffolding in Middle-School Mathematics PDF
Rizwaan Malik, Dorna Abdi, Rose E. Wang, Dora Demszky
Learning at Scale (L@S 2024); Under journal submission.
Winner of 2024 Tools Competition 🏆
Featured in The Learning Agency
Backtracing: Retrieving the Cause of the Query PDF Poster Video Code
Rose E. Wang, Pawan Wirawarn, Omar Khattab, Noah Goodman, Dora Demszky
European Chapter of the Association for Computational Linguistics (EACL 2024) Long Paper Findings
Featured in Stanford HAI
Does Feedback on Talk Time Increase Student Engagement? Evidence from a Randomized Controlled Trial on a Math Tutoring Platform PDF
Dora Demszky, Rose E. Wang, Sean Geraghty, Carol Yu
Learning Analytics and Knowledge Conference (LAK '24)
Problem-Oriented Segmentation and Retrieval: Case Study on Tutoring Conversations PDF
Rose E. Wang, Pawan Wirawarn, Kenny Lam, Omar Khattab, Dora Demszky
Conference on Empirical Methods in Natural Language Processing (EMNLP 2024) Long Paper Findings.
Evaluating Language Model Math Reasoning via Grounding in Educational Curricula PDF Code
Li Lucy, Tal August, Rose E. Wang, Luca Soldaini, Courtney Allison, Kyle Lo
Conference on Empirical Methods in Natural Language Processing (EMNLP 2024) Long Paper Findings.
Is ChatGPT a Good Teacher Coach? Measuring Zero-Shot Performance For Scoring and Providing Actionable Insights on Classroom Instruction PDF Video Code
Rose E. Wang, Dora Demszky
Innovative Use of NLP for Building Educational Applications (BEA 2023)
Ambassador (Best) Paper 🏆
SIGHT: A Large Dataset on Student Insights Gathered from Higher Education Transcripts PDF Video Code
Rose E. Wang*, Pawan Wirawarn*, Noah Goodman, Dora Demszky
Innovative Use of NLP for Building Educational Applications (BEA 2023)
“Mistakes Help Us Grow”: Facilitating and Evaluating Growth Mindset Supportive Language in Classrooms PDF Code
Kunal Handa, Margaret Clapper, Jessica Boyle, Rose E. Wang, Diyi Yang, David Yeager, Dora Demszky.
Conference on Empirical Methods in Natural Language Processing (EMNLP 2023)
Featured in Stanford HAI
Language modeling via stochastic processes PDF Video Code
Rose E. Wang, Esin Durmus, Noah Goodman, Tatsu Hashimoto
ICLR 2022
Oral Presentation (<1.6%)
Calibrate your listeners! Robust communication-based training for pragmatic speakers PDF Video Code
Rose E. Wang, Julia White, Jesse Mu, Noah Goodman
Conference on Empirical Methods in Natural Language Processing (EMNLP 2023) Findings
ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Reward PDF Code
Zixian Ma, Rose E. Wang, Fei-Fei Li, Michael Bernstein, Ranjay Krishna
Conference on Neural Information Processing Systems (NeurIPS 2022)
In the ZONE: Measuring difficulty and progression in curriculum generation PDF Video
Rose E. Wang, Jesse Mu, Dilip Arumugam, Natasha Jaques, Noah Goodman
NeurIPS 2022 Deep Reinforcement Learning Workshop
CLaP: Conditional Latent Planners for Offline Reinforcement Learning PDF
Harry Shin, Rose E. Wang
NeurIPS 2022 Workshop on Foundation Models for Decision Making
Speaking with confidence: Investigating the effects of uncertainty in pragmatic language learning Poster
Pawan Wirawarn, Rose E. Wang, Noah Goodman
Know Thy Student: Interactive Learning with Gaussian Processes PDF
Rose E. Wang, Mike Wu, Noah Goodman
ICLR 2022 Workshop on From Cells to Societies: Collective Learning across Scales
On the Opportunities and Risks of Foundation Models PDF
Center for Research on Foundation Models
Journal for Machine Learning Research (JMLR 2023)
Too many cooks: Bayesian inference for coordination multi-agent collaboration PDF Video Code
Rose E. Wang*, Sarah Wu*, Joshua Tenenbaum, James Evans, David Parkes, Max Kleiman-Weiner
Topics in Cognitive Science (2021); Human-Like Machine Intelligence (Oxford University Press)
Best Paper Award, CogSci 🏆; Best Paper Award, NeurIPS Cooperative AI Workshop 🏆
This website uses the website design and template by Martin Saveski