analiza aiqbench
This paper introduces Bayesian distillation with Behavioral Tuning (BBT), a novel framework that merges the interpretability of Bayesian models with the flexibility of neural networks to improve predictions of human behavior. By first distilling a neural network from a Bayesian model and then fine-tuning it on real-world data, the approach successfully captures complex heuristics and biases while maintaining rigorous inductive biases. This advancement represents a significant step forward in hybrid modeling paradigms for cognitive science and machine learning applications.
More accurate behavioral predictions with hybrid Bayesian-connectionist models
arXiv:2608.22154v1 Announce Type: new Abstract: Researchers must often choose between Bayesian or neural network models of behavior, two paradigms with complementary strengths and weaknesses. An ideal paradigm would facilitate testing many kinds of representations and inductive biases; Bayesian models make this easy, while neural networks do not. Similarly, an ideal paradigm would avoid over-simplifications; neural networks make this easy, while Bayesian models do not. Here, we introduce Bayesian distillation with Behavioral Tuning (BBT) as an approach to getting the best of both traditions. BBT offers a simple recipe for model building: first, a neural network is trained to mimic a Bayesian model through synthetic data, and second, the network is fine-tuned on human behavior to capture additional structure and nuance. Across four case studies in human concept learning, we find that BBT outperforms traditional approaches at predicting human behavior while also revealing psychological insights, resulting in models that can both mimic Bayesian priors and capture heuristics and biases that violate simple modeling assumptions.
Abstract:Researchers must often choose between Bayesian or neural network models of behavior, two paradigms with complementary strengths and weaknesses. An ideal paradigm would facilitate testing many kinds of representations and inductive biases; Bayesian models make this easy, while neural networks do not. Similarly, an ideal paradigm would avoid over-simplifications; neural networks make this easy, while Bayesian models do not. Here, we introduce Bayesian distillation with Behavioral Tuning (BBT) as an approach to getting the best of both traditions. BBT offers a simple recipe for model building: first, a neural network is trained to mimic a Bayesian model through synthetic data, and second, the network is fine-tuned on human behavior to capture additional structure and nuance. Across four case studies in human concept learning, we find that BBT outperforms traditional approaches at predicting human behavior while also revealing psychological insights, resulting in models that can both mimic Bayesian priors and capture heuristics and biases that violate simple modeling assumptions.
Machine Learning (cs.LG)
arXiv:2608.22154 [cs.LG]
(or arXiv:2608.22154v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.22154 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 252 cuvinte
Subiecte conexe
The Entangled Dimensions of Decision Theory
LessWrong · 30 iul. 2026
Taboo “equilibrium”: Less confused frames for research on AI bargaining
LessWrong · 31 iul. 2026
News
Quantum Computing Report · 25 iul. 2026
Condition aware learning enables robust prediction of oligonucleotide melting behavior across diverse chemistries and assay conditions
arXiv · 9 sept. 2026