🚨New Paper: LLM developers aim to align models with values like helpfulness or harmlessness. But when these conflict, which values do models choose to support? We introduce ConflictScope, a fully-automated evaluation pipeline that reveals how models rank values under conflict.
(📷 xkcd)

Honored to be promoted to Associate Professor at the University of Washington! Grateful to my brilliant mentees, students, collaborators, mentors & @techpolicylab.bsky.social for advancing research in AI & Ethics together—and for the invaluable academic freedom to keep shaping trustworthy AI.

🔗 Paper: aclanthology.org/2025.naacl-l...

Work done with amazing collaborators
@isaacslaughter.bsky.social,
@kyrawilson.bsky.social, @aylincaliskan.bsky.social, and @monadiab77.bsky.social!

Catch our Oral presentation at Ballroom B, Thursday, May 1st, 14:00-15:30 pm!📷✨

🔗 Paper: aclanthology.org/2025.naacl-l...

Work done with amazing collaborators
@isaacslaughter.bsky.social,
@kyrawilson.bsky.social, @aylincaliskan.bsky.social, and @monadiab77.bsky.social!

Catch our Oral presentation at Ballroom B, Thursday, May 1st, 14:00-15:30 pm!📷✨

Excited to announce our #NAACL2025 Oral paper! 🎉✨

We carried out the largest systematic study so far to map the links between upstream choices, intrinsic bias, and downstream zero-shot performance across 131 CLIP Vision-language encoders, 26 datasets, and 55 architectures!

🖼️ ↔️ 📝 Modality shifts biases: Cross-modal analysis reveals modality-specific biases, e.g. image-based 'Age/Valence' tests exhibit differences in bias directions; pointing to the need for vision-language alignment, measurement, and mitigation methods.

📊 Bias and downstream performance are linked: We find that intrinsic biases are consistently correlated with downstream task performance on the VTAB+ benchmark (r ≈ 0.3–0.8). Improved performance in CLIP models comes at the cost of skewing stereotypes in particular directions.

⚠️ What data is "high" quality? Pretraining data curated through automated or heuristic-based data filtering methods to ensure high downstream zero-shot performance (e.g. DFN, Commonpool, Datacomp) tend to exhibit the most bias!

📌 Data is key: We find that the choice of pre-training dataset is the strongest predictor of associations, over and above architectural variations, dataset size & number of model parameters.

1. Upstream factors:  How do dataset, architecture, and size affect intrinsic bias?
2. Performance link : Does better zero-shot accuracy come with more bias?
3. Modality: Do images and text encode prejudice differently?

We sought to answer some pressing questions on the relationship between bias and model design choices and performance👇

🔧 Our analysis of intrinsic bias is carried out with a more grounded and improved version of the Embedding Association Tests with controlled stimuli (NRC-VAD, OASIS). We reduced measurement variance by 4.8% and saw ~80% alignment with human stereotypes in 3.4K tests.

🚨 Key takeaway: Unwanted associations in Vision-language encoders are deeply rooted in the pretraining data and how it is curated and careful reconsideration of these methods is necessary to ensure that fairness concerns are properly addressed.

Excited to announce our #NAACL2025 Oral paper! 🎉✨

We carried out the largest systematic study so far to map the links between upstream choices, intrinsic bias, and downstream zero-shot performance across 131 CLIP Vision-language encoders, 26 datasets, and 55 architectures!

🗞️ Hot off the press! 🗞️
@aylincaliskan.bsky.social and I wrote a blog post about how to make resume screening with AI more equitable based findings from our work presented at AIES in 2024. Major takeaways ⬇️ (1/6)

www.brookings.edu/articles/gen...

UW’s @techpolicylab.bsky.social and I invite applications for a 2-year Postdoctoral Researcher position in "AI Alignment with Ethical Principles" focusing on language technologies, societal impact, and tech policy.

Kindly share!
apply.interfolio.com/162834
Priority review deadline: 3/28/2025

Looking for all your LTI friends on Bluesky? The LTI Starter Pack is here to help!

go.bsky.app/NhTwCVb