Juliette Woodrow (@juliettewoodrow) 's Twitter Profile
Juliette Woodrow

@juliettewoodrow

CS PhD Student @Stanford. My research focuses on how we can leverage human-centered AI to improve access to education.

ID: 1768405840774721536

linkhttps://juliettewoodrow.github.io/ calendar_today14-03-2024 22:36:30

14 Tweet

103 Takipçi

94 Takip Edilen

Krista Opsahl-Ong (@kristahopsalong) 's Twitter Profile Photo

Got a pipeline with **multiple prompts**, like a DSPy program? What's the right way to jointly optimize these prompts? Introducing MIPRO, a Multi-prompt Instruction Proposal Optimizer. We integrated MIPRO into DSPy. It can deliver +11% gains over existing DSPy optimizers! 🧵👇

Chris Piech (@chrispiech) 's Twitter Profile Photo

Code in Place 4 is on! Do you know anyone who wants to learn python? Know anyone who wants to teach? Share this class with them. It's a wonderful vibe.

Chris Piech (@chrispiech) 's Twitter Profile Photo

Going to #sigcse2024? A group of students from the lab will be presenting papers (many are considering careers in teaching + research). Come to their talks and say hi! Talk times and locations: tinyurl.com/sigcse2024 Learners Teaching Novices: An Uplifting Alternative

Chris Piech (@chrispiech) 's Twitter Profile Photo

Congratulations Sierra Wang and the whole team who made the IDE / course. For a demo, try making a syntax error on codeinplace.stanford.edu... Great #sigcse2024 PDX

Congratulations <a href="/sierracwang/">Sierra Wang</a> and the whole team who made the IDE / course. For a demo, try making a syntax error on codeinplace.stanford.edu... Great #sigcse2024 PDX
Ali Malik (@malikrali) 's Twitter Profile Photo

Had a great time at #sigcse2024 presenting our work on having students teach as a novel form of assessment that is fulfilling, deepens understanding, and also helps others! Joint work with my amazing collaborators Juliette Woodrow and Chris Piech. dl.acm.org/doi/10.1145/36…

Nicole Meister (@nicole__meister) 's Twitter Profile Photo

Prior work has used LLMs to simulate survey responses, yet their ability to match the distribution of views remains uncertain. Our new paper [arxiv.org/pdf/2411.05403] introduces a benchmark to evaluate how distributionally aligned LLMs are with human opinions. 🧵

Prior work has used LLMs to simulate survey responses, yet their ability to match the distribution of views remains uncertain.

Our new paper [arxiv.org/pdf/2411.05403] introduces a benchmark to evaluate how distributionally aligned LLMs are with human opinions.

🧵
Teddi Worledge (@teddiworledge) 's Twitter Profile Photo

🧵LLMs are great at synthesizing info, but unreliable at citing sources. Search engines are the opposite. What lies between them? Our new paper runs human evals on 7 systems across the✨extractive-abstractive spectrum✨for utility, citation quality, time-to-verify, & fluency!

🧵LLMs are great at synthesizing info, but unreliable at citing sources. Search engines are the opposite. What lies between them?

Our new paper runs human evals on 7 systems across the✨extractive-abstractive spectrum✨for utility, citation quality, time-to-verify, &amp; fluency!
Sanmi Koyejo (@sanmikoyejo) 's Twitter Profile Photo

Improving Suggestions For Student Feedback Using Direct Preference Optimization (DPO) by Juliette Woodrow presents a method for producing LLM-generated feedback suggestions that align with human preferences through an iterative fine-tuning process. juliettewoodrow.github.io/paper-hosting/… 2/n

Juliette Woodrow (@juliettewoodrow) 's Twitter Profile Photo

I read 95 books in 2024 (but at what cost… social life? sanity? who’s to say). These were some of my favorites: 📗 The Sign for Home by Blair Fell 📗 The Anthropocene Reviewed by John Green 📗 The Six by Loren Grush Share any recs for me to read in 2025!