Connor Baumler @ctbaumler

PhD student @clipumd @umdcs | 🏳️‍⚧️🏳️‍🌈 ctbaumler.github.io Joined June 2022

Tweets

42
Followers

146
Following

268
Likes

170

Connor Baumler @ctbaumler

2 days ago

Interested in hearing more? I'll be presenting about this work in Poster Session A tomorrow (7/5) at 11AM. #ACL2026

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.

10 40 236 30K 101

0 5 17 3K 3

View Details

Pangram @pangram

2 months ago

10 40 236 30K 101

View Details

Haozhe An @haozhean36

a year ago

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. 📊

1 4 9 777 2

View Details

CLS @ChengleiSi

2 years ago

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.

94 743 4K 1.1M 3K

View Details

Seraphina Goldfarb-Tarrant @seraphinagt

2 years ago

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

1 2 8 597 1

View Details

Trista Cao @Triiiiiista

2 years ago

🚨Our latest work reveals the needs of volunteer content moderators and the gaps in current AI tools. Many existing models focus on toxicity detection but fail to address many other moderation rules. Time to rethink and expand to better support moderators! 🚫🤖

1 6 16 3K 1

View Details

Connor Baumler @ctbaumler

2 years ago

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]

0 0 1 134 1

View Details

Connor Baumler @ctbaumler

2 years ago

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 0 1 134 0

View Details

Connor Baumler @ctbaumler

2 years ago

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 🧵