Summary of Centaur: a Foundation Model Of Human Cognition, by Marcel Binz et al.
Centaur: a foundation model of human cognition
by Marcel Binz, Elif Akata, Matthias Bethge, Franziska Brändle, Fred Callaway, Julian Coda-Forno, Peter Dayan, Can Demircan, Maria K. Eckstein, Noémi Éltető, Thomas L. Griffiths, Susanne Haridi, Akshay K. Jagadish, Li Ji-An, Alexander Kipnis, Sreejan Kumar, Tobias Ludwig, Marvin Mathony, Marcelo Mattar, Alireza Modirshanechi, Surabhi S. Nath, Joshua C. Peterson, Milena Rmus, Evan M. Russek, Tankred Saanum, Natalia Scharfenberg, Johannes A. Schubert, Luca M. Schulze Buschoff, Nishad Singhi, Xin Sui, Mirko Thalmann, Fabian Theis, Vuong Truong, Vishaal Udandarao, Konstantinos Voudouris, Robert Wilson, Kristin Witte, Shuchen Wu, Dirk Wulff, Huadong Xiong, Eric Schulz
First submitted to arxiv on: 26 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper introduces Centaur, a computational model that can predict and simulate human behavior in various experiments expressed in natural language. The model is derived from a state-of-the-art language model finetuned on Psych-101, a large-scale dataset covering over 60,000 participants performing choices in 160 experiments. Centaur outperforms existing cognitive models in capturing held-out participant behavior and generalizes well to new domains. The internal representations of the model become more aligned with human neural activity after finetuning. This unified model of human cognition has the potential to disrupt the cognitive sciences by challenging the current paradigm for developing computational models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research creates a new computer model called Centaur that can understand and predict how humans behave in different situations. The team used a huge dataset with information from over 60,000 people doing various tasks to train the model. This model is special because it’s not just good at predicting human behavior but also works well in new situations. It even starts to think like our brains do after learning from data! This breakthrough has the potential to change how we understand human thinking and behavior. |
Keywords
* Artificial intelligence * Language model
