New preprint uses methods from psychology to explore implicit biases in large language models. Using simple prompts that probe associations between social categories, models that have been trained to be explicitly unbiased show systematic biases.

I am looking forward to presenting this work at #ICLR2024 (Tue. 10:45am-12:45pm Halle B #201).

Anyone interested in Bayesian inference (from the optimization perspective), meta-learning, and inductive bias? I would love to chat!

Paper: openreview.net/forum?id=auUng…

New paper! Cognitive science has a long tradition of thinking about the tradeoffs inherent in language, which can give us useful tools for understanding large language models. While we want our models to be honest and helpful, sometimes those goals conflict.

Princeton is hiring postdocs interested in projects focused on comparing AI systems to human cognition or using ideas from cognitive science to better understand those systems as part of a new initiative studying Natural and Artificial Minds. Apply at puwebp.princeton.edu/AcadHire/posit…

💡Can LLMs like GPT-4 reason creatively? Excited to share our latest research on AI and creativity! 🚀 Introducing MacGyver: a new playground for everyday innovation and physical reasoning --we collect problems to trigger unconventional usage of objects and innovative solutions.

Being able to collect large amounts of behavioral data allows us to revisit classic results in cognitive psychology established with simple laboratory stimuli to see whether they hold with more naturalistic stimuli. Shepard's law is just as beautiful for real images.

Do Large Language Models (LLM) have leadership? Together with cognitive scientists Tom Griffiths Griffiths Computational Cognitive Science Lab and Natalia Velez Natalia Vélez (natvelali @ 🧵/🟦/fediscience.org) at Princeton University, we created a multi-LLM-agent system to test if agents work better with a leader. It turns out that LLMs do have leadership,

In this fun new paper we use a programming game to explore people's preferences for the structure of hierarchical plans.

New paper! Nudging has been a popular way to guide people's decisions, but it doesn't always work. We present a framework that allows us to predict when nudges will be effective and test them in a controlled setting. We then use this framework to optimize for effective nudges.

Come join us! New postdoctoral position in computational cognitive science, with specific interest in applications of large language models in cognitive science and use of Bayesian methods and metalearning to understand human cognition and AI systems.

princeton.edu/acad-positions…

New preprint w/ Fred Callaway Griffiths Computational Cognitive Science Lab

osf.io/preprints/psya…

We show that simulated data from cognitive models can be used to pretrain neural networks to infer an individual's preferences from their fixations.

Introducing Gaussian Process Probes (GPP) for probing and measuring uncertainty about concepts represented by AI models. #NeurIPS poster #1504 this Tue at 5pm!

Paper: arxiv.org/abs/2305.18213

Joint work with Alexander Ku, Jason Baldridge, Tom Griffiths Griffiths Computational Cognitive Science Lab and Been Kim (General Chair-ing ICLR2024 ✈️)

🧵 Excited to share another new paper with Griffiths Computational Cognitive Science Lab, accepted as a spotlight at #NeurIPS2023 ! 🎉 We delve into the intriguing intersection of AI and human cognition, exploring how alignment with human representations impacts few-shot learning tasks.🧠🤖🎓 Let's unpack this!👇