Joined June 2022
- Tweets42
- Following270
- Followers154
- Likes175
Connor Baumler retweeted
🚨 New Paper! 🚨
Your agent is writing code faster than you can understand it 😬
In our controlled online study, coding agents helped users finish tasks quickly, but reduced how well they understood the code they just “wrote”
We also find three ways to avoid this tradeoff 👇🧵
Connor Baumler retweeted
Excited to share two papers at #EMNLP2026! 🥳
1️⃣ Check the Scoreboard: We extend *scoring schemes* from education research and validate their benefits for LLM evals (Main) 🧑🏫📈
2️⃣ VibeJam: Our system for human-AI studies with coding agents (Demo) 🧑💻🌐
See you in Budapest! 🤠
ALT emnlp :)
Interested in hearing more? I'll be presenting about this work in Poster Session A tomorrow (7/5) at 11AM. #ACL2026
Connor Baumler retweeted
Can you edit AI writing to sound like you?
In collaboration with Pangram, researchers at the University of Maryland found that even after editing, LLM text remained more similar to AI writing than to human — despite editor's reports that the edited text reflected their voice.
Connor Baumler retweeted
Ever wonder how LLMs perceive gender from first names (and occupations)? 🤔
🔗 arxiv.org/abs/2503.06792
Our paper (w/ @ctbaumler, @AbhilashaSanch2, @rachelrudinger) finds that:
(1) LLMs representations of gender for first names mirror real-world gender distributions. 📊
Connor Baumler retweeted
Automating AI research is exciting! But can LLMs actually produce novel, expert-level research ideas?
After a year-long study, we obtained the first statistically significant conclusion: LLM-generated ideas are more novel than ideas written by expert human researchers.
Connor Baumler retweeted
A cool graphic from @haldaume3 @genderbiasnlp keynote: the impact of text completion on stereotypes stories. Pro stereotyped suggestions are the same or worse than no text completion, but anti stereotype can reduce it. #ACL2024
Explanations are sought to highlight model biases. But what if these biases are indirect? Our #IUI2024 paper studies how people make decisions with models exhibiting direct or indirect bias. Can explanations and disclosures about biases/correlations help mitigate these biases 🧵
ALT Screenshot of paper title and authors. "The Impact of Explanations on Fairness in Human-AI Decision-Making: Protected vs Proxy Features"
Based on these findings, if you are going to show people explanations of model output, we recommend contextualizing the explanations with potential model biases and proxies. [12/13]
1
1
134
This project was co-led with the inimitable @navitagoyal_ in collaboration with Tin Nguyen and @haldaume3. You can check out the full paper here: arxiv.org/abs/2310.08617 If you're at IUI, you can check out the talk Tuesday at 3:50 [13/13]
1
134