6 papers
Thought without systematicity? Evaluating reasoning models on rule induction tasks
Simon Schug, Brenden M. Lake
A central tenet of human cognition is systematicity, the principle that understanding one concept is inherently tied to understanding close variations of that concept. Do reasoning…
More accurate behavioral predictions with hybrid Bayesian-connectionist models
Brenden M. Lake, Akshay K. Jagadish, Guangyuan Jiang
Researchers must often choose between Bayesian or neural network models of behavior, two paradigms with complementary strengths and weaknesses. An ideal paradigm would facilitate t…
Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models
Liyi Zhang, Akshay K. Jagadish, Brenden M. Lake +1
Post-training Large Language Models (LLMs) for reasoning typically focuses on deductive tasks such as mathematics and coding where correctness is verifiable. Yet, many real-world r…
Investigating Concept Alignment Using Implausible Category Members
Sunayana Rane, Brenden M. Lake, Thomas L. Griffiths
Developing AI systems with a human-like understanding of everyday concepts is a key step towards developing safe, reliable systems whose behavior makes sense to humans. When probin…
Are they human? Detecting large language models by probing human memory constraints
Simon Schug, Brenden M. Lake
The validity of online behavioral research relies on study participants being human rather than machine. In the past, it was possible to detect machines by posing simple challenges…
An explainable transformer circuit for compositional generalization
Cheng Tang, Brenden Lake, Mehrdad Jazayeri
Compositional generalization-the systematic combination of known components into novel structures-remains a core challenge in cognitive science and machine learning. Although trans…