10 years after the initial idea, Artificial Humanities is here! Thanks so much to all who have preordered it. I hope you enjoy reading it and find this research approach as generative as I do. More to come!

🏳️‍🌈🎨💻📢 Happy to share our workshop study on queer artists’ experiences critically engaging with GenAI

Looking forward to presenting this work at #FAccT2025 and you can read a pre-print here:
arxiv.org/abs/2503.09805

When it comes to text prediction, where does one LM outperform another? If you've ever worked on LM evals, you know this question is a lot more complex than it seems. In our new #acl2025 paper, we developed a method to find fine-grained differences between LMs:

🧵1/9

🖋️ Curious how writing differs across (research) cultures?
🚩 Tired of “cultural” evals that don't consult people?

We engaged with interdisciplinary researchers to identify & measure ✨cultural norms✨in scientific writing, and show that❗LLMs flatten them❗

📜 arxiv.org/abs/2506.00784

[1/11]

This looks incredible! Thanks for sharing the syllabus!

I’m thrilled to share RewardBench 2 📊— We created a new multi-domain reward model evaluation that is substantially harder than RewardBench, we trained and released 70 reward models, and we gained insights about reward modeling benchmarks and downstream performance!

I'm joining Wisconsin CS as an assistant professor in fall 2026!! There, I'll continue working on language models, computational social science, & responsible AI. 🌲🧀🚣🏻‍♀️ Apply to be my PhD student!

Before then, I'll postdoc for a year in the NLP group at another UW 🏔️ in the Pacific Northwest

When interacting with ChatGPT, have you wondered if they would ever "lie" to you? We found that under pressure, LLMs often choose deception. Our new #NAACL2025 paper, "AI-LIEDAR ," reveals models were truthful less than 50% of the time when faced with utility-truthfulness conflicts! 🤯 1/

I updated our 🔭StorySeeker demo. Aimed at beginners, it briefly walks through loading our model from Hugging Face, loading your own text dataset, predicting whether each text contains a story, and topic modeling and exploring the results. Runs in your browser, no installation needed!
↳

New work on multimodal framing! 💫

Some fun results: comparisons of the same frame when expressed in images vs texts. When the "crime" frame is expressed in the article text, there are more political words in the text, but when the frame is expressed in the article image, more police words.

This was joint work with my co-author Zubin Aysola; collaborators @dchechel.bsky.social, Nick Deas, and @chryssazrv.bsky.social; and advisor @maartensap.bsky.social at @ltiatcmu.bsky.social @scsatcmu.bsky.social @columbiauniversity.bsky.social, and the @istecnico.bsky.social! (10/10)

Our work builds on sociolinguistic and NLP research on AAL and recent translation methods. Check out the paper for details! We hope others extend this work, e.g., to investigate or mitigate reward model biases against more dialects. (9/10)

These results point to representational and quality-of-service harms for AAL speakers. ⚠️They also highlight complex ethical questions about the desired behavior of LLMs concerning AAL. (8/10)

Finally, we show that the reward models strongly incentivize steering conversations toward WME, even when prompted with AAL. 🗣️🔄 (7/10)

Also, for most models, rewards are negatively correlated with the predicted AAL-ness of a text (based on a pre-existing dialect detection tool). (6/10)

Next, we show that most reward models predict lower rewards for AAL texts ⬇️ (5/10)

First, we see a significant drop in performance (-4% accuracy on average) in assigning higher rewards to human-preferred completions when processing AAL texts vs. WME texts. 📉 (4/10)

We introduce morphosyntactic & phonological features of AAL into WME texts from the RewardBench dataset using validated automatic translation methods. Then, we test 17 reward models for implicit anti-AAL dialect biases. 📊 (3/10)

We develop a framework for evaluating dialect biases in reward models and conduct a case study on biases against African American Language (AAL) relative to White Mainstream English (WME). 🔍 (2/10)

Reward models for LMs are meant to align outputs with human preferences—but do they accidentally encode dialect biases? 🤔

Excited to share our paper on biases against African American Language in reward models, accepted to #NAACL2025 Findings! 🎉

Paper: arxiv.org/abs/2502.12858 (1/10)